process of evaluating claims or hypotheses and making judgments about them on the basis of well-supported evidence
a prediction stated as a testable proposition, usually in the form of an if-then statement
a statement of the specific methods used to measure a variable; a detailed explanation of the variable
cluster of explanations of a phenomenon that help predict, explain, and control that behavior
method gathering descriptive information involving watching behaviors, without interfering, as they naturally occur
used to collect descriptive data through the intensive examination of a phenomenon in a particular individual, group, or setting (particularly useful for rare or complex phenomena)
questionnaire or interview administered to a large group; designed to obtain descriptions of peoples' behaviors/beliefs
research method that examines relationships between variables in order to analyze trends in data, test predictions, etc. (they do NOT discern cause and effect relationships)
the only research method to show causation, this involves obtaining a random sample of subjects and using control and experimental groups; allows a researcher to control the data-collection process
controlled by the researcher, experienced by the control group, this is what the researcher thinks will HAVE an effect on some other behavior
behavior affected by another variable, it is observed and measured (usually before and after and experiment takes place)
provides a baseline for comparison, does not receive critical treatment (independent variable)
occurs when experimenters ask leading questions or otherwise search for evidence that supports their hypothesis and don't look for evidence that refutes it
a confounding variable in which uncontrolled factors affected the dependent variable along with or instead of the independent variable
random distribution of participants to experimental or control groups - used to distribute the impact of uncontrolled variables randomly, and most likely evenly, across the groups, minimizing the chance they will distort the results
improvement caused by a participant's knowledge and expectations: can be from a treatment that contains nothing known to be helpful, but that nevertheless produces benefits because a person believes it will be beneficial.
any factor that affects the dependent variable, along with or instead of the independent variable
design for research in which neither the experimenter nor the subjects know who is in the experimental or control group
the process of selecing participants for research who are members of the population the researcher wishes to study
a group of subjects whose characteristics fairly reflect the characteristics of the population they belong to
a group of subjects selected froma population whose members all had an equal chance of being selected
a group of research subjects selected froma population whose members did not all have an equal chance of being chosen
when researchers draw participants from the populations that are readily available to them
study the heredity-environment question by comparing the similarity seen in identical twins with those of nonidentical pairs
set of mathematical procedures that help researchers learn if their research data reflects a true relationship or could be due to random chance
measure of variability that is the difference between the highest and lowest values in a set of data
measure of variability that is the average difference between each score and the mean of the data set (demonstrates consistency)
a statistic (r) that summarizes the strength and direction of a relationship between two variables
a term used to describe research results that have been shown by a statistical test to be UNLIKELY to be due to random chance
code used by psychologists dictating that they minimize discomfort or risk for research participants
statement of procedures used to define research variables which helps to enable replication
repeating of research study to determine if its finding extends to other participants and circumstances
descriptive research technique in which one person or a small group is studied in depth in hope of revealing universal principles
research method in which info is obtained by asking many individuals a fixed set of questions
false consensus effect
tendency to overestimate extent to which others share our beliefs and behaviors
sample that fairly represents a population because each member has an equal chance of inclusion.
descriptive research that involves observing and recording behavior without trying to manipulate and control the situation.
measure of the extent to which two factors vary together which can be positive or negative or non
graphed cluster of dots, each of which represents the values of two variables. The slope of the points suggests the direction of the relationship between the two variables.
research method in which investigator manipulates one or more factors (IV) to observe effect on some behavior or mental process (DV)
condition of experiment that contrasts with experimental condition and serves as a comparison for evaluating the effect of the treatment.
experimental procedure in which both research participants and research staff are ignorant about whether the research participants have received the treatment or a placebo.
condition of experiment that exposes participants to treatment, that is, to one version of the IV
experimental results caused by expectations alone; any effect on behavior caused by the administration of an inert substance or condition, which is assumed to be an active agent.
variable that may change in response to manipulations of the IV (what is measured)
experimental factor that is manipulated; variable whose effect is being studied.
statistical statement of how likely it is that an obtained result occurred by chance - expressed as p or sig.
Steps in the Research Process
1) select topic, 2) focus question, 3) design study, 4)collect data, 5) Analyze data, 6)interpret data, 7) inform others
What is a Research Question:
the organizing principle for an individual study. It clarifies exactly what the researcher wants to understand, describe, or explain
Characteristics of a Good Research Question:
1) It elicits an explanation or description, not an answer 2) It links contructs & suggests associations or relationships 3) It can be addressed w/ empirical evidence 4) It is focused and feasible
Patient/problem, intervention, comparison intervention, outcomes. Works best for quantitative designs
allow us to use sample data to estimate a population value like the ture mean or the true proportion. EX: what is the true avg amount students spend weekly on alcohol
Allows us to use sample data to test a claim about a population, such as testing whether a population proportion or population mean = some #. EX: is the true avg amount that students spent weekly on alcohol $20
always represents the status quo, i.e. the hypothesis that requires no change in current behavior.
Using the PubMed database
Identify the key concepts in your research question. Example: Find citations about bronchodilators for treating asthma in children.The key concepts are bronchodilators, asthma and children Enter the significant terms into the search box. Press the Enter key or click Go
Writing References in APA style
Author (alphabetical) month/year, journal name, article name, where it was retrieved
Difference between a literature review and a research paper
Research paper - supports your own argument. Literature review-summary and synthesis of the arguments and ideas of others
Literature review strategies
Find a focus - organize around an idea, Construct a working thesis statement, Organize: Basic categories include: Introduction Body Conclusions Organizing the body methods include: Chronological, Thematic, Methodological
a declarative sentence which summarizes the specific topic and goals of a document. It is typically included in the introduction to give the reader an accurate, concrete understanding what the document will cover and what he/she can gain from reading it. To be effective it should be: specific and precise, concise, clear, goal oriented
Keys to a Successful Presentation:
Define Objectives, Know Your Audience, Organize Your Presentation, Develop Visual Aids, Address Your Delivery, Develop Your Q&A, Check Out Your Environment
Report of Literature Search, Methodology/Techniques, Results, Interpretation/Discussion, Future Implications
The 3 step outline of a presentation
Step One: Tell them what you will tell them Step Two: Tell them Step Three: Tell them what you told them
Importance of visual aids
Increase Audience Interest, Focus Audience Attention, Induce Audience Participation, Reinforce Points of Emphasis, Increase Retention of Content
Effective delivery factors
Enthusiasm, Audience Bonding, Posture/Movement, Gestures, Eye Contact, Voice Quality
Hazards of presentations
Poor Introduction, Equipment Failure, Missing Materials, Lighting, Hecklers, Late Returners
Effective/Ineffective purpose statement: "The purpose of this paper is to describe the changes that are occurring in corporate America
ineffective: too vague
Ineffective/effective purpose statement:"The purpose of this report is to discuss the eating disorders Anorexia and Bulimia
Ineffective: to vague
ineffective/effective purpose statement: This article will cover the different ways a company can become organized
Ineffective: obscure and misleading
Ineffective/effective purpose statement:This paper will describe four common causes of co-worker conflict in organizations and explain how to use a five-step procedure to constructively manage this conflict
effective: very specific
Ineffective/effective purpose statement: This report will explain how supervisors can use four planning strategies to improve employee productivity in the workplace
effective: very specific
Ineffective/effective purpose statment: This purpose of this report is to describe the main causes of traffic congestion in Seattle
Effective: leaves no doubt about the reporters main purpose
3 Principles: Beneficence, Respect, Justice 6 Norms: Valid Research Design, Researcher Competence, Identify Consequences, Appropriate Sample Selection, Voluntary Informed Consent, Inform Participants whether harm will be compensated
Debriefing, Dehoaxing, Guarding Privacy & Confidentiality of Participants, Obtain fully informed consent
maximizing good outcomes for science, humanity, and the individual research participants & minimizing or avoiding unnecessary risk, harm, or wrong
agree to participate without threat or undue inducement knowing what a reasonable person in the same situation would want to know before giving consent & explicitly agreeing to participate
assignment of subjects/participants so that both the criteria of equal probability and independence are fullfilled
the selection of each unit is independent of the selection of any other unit; every person in a population has equal probability of being selected
Defining Characteristics of Experimental Research
1) change x & observe y 2) control as many variables as possible, manipulate 1 to yield causation 3) results are interpreted as "true" within a certain degree of probability
other factors that can affect an outcome in an experiment- not measured, but explains results
a variable that is managed or manipulated in an experiment to determine whether it affects a dependent variable
a variable that is observed or measured in an experiment to determine whether it is affected by an independent variable
a variable being studied in a correlational project, regarding the extent to which it is correctly predicted by one or more predictor variables
a variable being studied in a correlational project, regarding the extent to which it correctly predicts one or more criterion varialbes
an aspect of design validity: the extent to which all extraneous variables are controlled, enabling results to be interpreted unambiguously regarding the people, setting & occasions studied
Generalizability of results to other people, times, places & circumstances than those studied, as relevant to the project's mission
a statistical hypothesis of "no difference" or "no relation" in populations represented by the samples
a statement that expresses a prediction about what the answer to a research question will be or an idea about the phenomenon being studied
composed of subjects that are alike in all preexisting characteristics to the experimental group, except for the treatment experienced by the experimental group
a statistical measure expressing the relationship between two or more variables with a single number between 1 & 1, inclusive
Cross Sectional Research
"cohort design" based on independent group comparisons among samples who have reached different stages of development at the time the study is conducted
studies the same people at different times; inferences about the developmental variable are based on repeated measures comparisons
descriptive research approach- studies intensively a given social unit (individual, group, institution, etc.)
research method designed to describe & analyze practices & beliefs of cultures & communities; involves entering into first hand interaction with people in their everyday lives
participants participate in the research process- Cooperative Inquiry or Participatory Action Research
Threats to Internal Validity
1) History 2) Maturation 3) Testing 4) Instrumentation 5) Statistical Regression 6) Differential Selection 7) Experimental Mortality 8) Selection-Maturation Interaction 9) Experimental Treatment Diffusion 10) Compensatory Rivalry by Control Group- John Henry Effect 11) Compensatory Equalization Diffusion 12) Resentful Demoralization of the Control Group
a method of sampling in which the population is subdivided according to one or more stratification variables before the sample is selected, each subdivision of the population is represented by a corresponding subdivision in the sample
sites or individuals are selected in which the phenomenon of interest is strongly represented , but not necessarily extreme
Simple Random Sampling
random sampling applied to the entire frame at once; requires access to the entire population-every person has equal probability of being selected
sample is drawn in such a way that makes it probable that the sample is approximately the same as the population on the variables to be studied (SRS, systematic, stratified, cluster, multistage)
a set of individuals studied in a research project because they are conveniently available, without regard to whether they are representative of a population
experimentally accessible population; moving from a theoretical definition of a concept to something that can be measured; practical, measurable
a theoretical definition of a concept that uses other constructs to explain the meaning
reality is socially constructed, research-attempt to understand from POV of those experiencing ; research can not be separated from researcher bias
rational, empiricist, value free & causal nature of what we observe can be concluded; prefer experimental design & random assignment
refer to the percentage of cases in a norm sample who scored below an individual's score
have instructions for uniform administration, procedures and norms & have been put through rigorous developmental cycles
Meaning of p Values
Power-ability to detect deviations from the null hypothesis; ex. .5% chance will detect statistical significance if it is present
of a magnitude rarely obtained by random sampling from populations for which the null hypothesis is true; probability that the difference in scores occurred because of reasons other than error
Norm Referenced Tests
individuals performances can be compared with the norm group; results from 1 or more large samples with known characteristics
analysis of variance- a test for the significance of differences among three of more means; parametric
defines a line of best fit for correlational data that can be used as a prediction equation
clustered vs. distributed neurons
two binary choices that will decide between localizationist and holist positions; functionally homogeneous neurons are either one or the other
shared vs. dedicated neurons
neurons perform duties 'across functions' or are solely devoted to a specific language function
what you use to make measurements; i.e. words to write, read, etc. when studying aphasia
the results of what you are testing; errors and correct answer, how long it takes to answer correctly, etc. when studying aphasia
box and arrow flowchart, not like neuroanatomy, based on a patient's performance on multi-related language tasks, from sensory input (visual/auditory) to output (written/spoken)
using scalp electrodes, small electrical responses to specific inputs can only be observed by averaging the EEG traces over a series of trials
content words or "open class"
carry meaning; numerous; variable lengths; can add new ones to language; mainly consist of nouns, verbs, adjectives, adverbs
function words or "closed class"
do not carry meanings by themselves; can't add new ones to language, usually small words (grammatical morphemes and endings); articles, conjunctions, prepositions, pronouns, quantifiers
Broca's aphasics show evidence for selective loss of closed class words while retaining open class
add blood volume flow analysis: oxygenated blood has different magnetic properties relative to de-oxygenated blood, hence bigger signal
practicing and repeating an experimental task can affect blood flow over a few trials. So test and control must have the same effect.
by subtracting a "control state" from the current "stimulus state" one could isolate areas of activation related to mental operations present in the stimulus state, but not in the control state
A decision made by the researcher about whether the hypothesis was supported based on the results obtained in an experiment
the ethical principle whereby a professional does not disclose to others information n given in confidence to them by a client/patient. In research studies, personal information should only be collected if it is relevant to the study and can only be reported in such a way that subjects' identities are not revealed. If subjects are dissatisfied after debriefing, they can demand that their data is destroyed. (In therapeutic situations, the patient's consent is required before the practitioner can disclose any information of a personal nature. Exceptions to this occur in cases with minors where discussions are held with parents or in cases where the client threatens, either directly or through their behaviour, to cause harm to themselves or others, in which case the professional is obligated to attempt to prevent such an occurrence.)
An unwanted factor occurring in the procedures, experimenters or subjects in an experiment that has an effect on the dependent variable, along with or instead of the dependent variable.
A condition in an experiment used as a baseline or comparison with the experimental condition involving the treatment variable. Thus, subjects experiencing the control condition should be identical in characteristics and experience similar standardised conditions to those experiencing the experimental condition; however they should not experience the independent variable.
A group for which all conditions are identical to those of the experimental group except that participants are not exposed to the manipulation of the independent variable. This enables the researcher to determine whether the independent variable has affected the dependent variable.
A type of extraneous variable whose influence has been removed from the research via sampling, experimental method and/or statistical control.
The process of selecting members of a population to participate in research who are easily obtainable. Examples include newspaper polls and radio station phone-ins, as well as approaching individuals in a shopping centre. Such a sample may not be representative of the population as individuals actively volunteering to participate in the study, or drawn from a narrow strata of the population, may be biased.
A statistical measure of the strength and direction of the relationship between two variables, events or measures that occur together so that changes in one are accompanied by changes in the other. It is not a causative measure, meaning that it does not explain the reason behind a relationship between two variables.
An indication of the strength and direction of a correlation between two variables. It ranges from -1.00, indicating a strong negative relationship to, + 1.00, indicating a strong positive relationship. 0.00 indicates no correlation. Furthermore, a correlation level of 0.05 is needed in order to consider a correlation as being moderately strong, an indication of statistical significance.
A research method that identifies and describes the relationship between two variables, events or measures.
Research in which individuals of differing ages drawn from a representative sample are compared in a single study.
Reversing the order of presentation for half the participants so that fatigue and practice effects occur in different orders to 'balance' their effects
Feedback given to experimental subjects about the purposes and results of the research of which they were a part. Such feedback should remove any misconceptions caused by deception within the experimental design, and should provide results and interpretations to the participants. The aim is to ensure that subjects leave the experiment in as similar a state as possible as they entered it.
Statistics that describe or summarise the data and typically include a measure of central tendency and dispersion
Dependent variable (DV)
A factor or characteristic of a subject's behaviour or experience that can be observed or measured as being changed in some way as a result of being manipulated by the independent variable. This measure is obtained to test the outcome of the experiment.
A research method involving investigating overt or directly measurable behaviour through the process of watching and recording it as it occurs.
A test in which neither the experimenters or subjects are aware of which subjects have been allocated to the experimental group.
A set of moral principles and practices that have been used by psychologists to provide guidelines relating to what is acceptable conduct in terms of right or wrong that researchers follow when considering using humans or animals as research subjects.
-A method of data collection used to systematically measure the relationship between variables which have been operationalised in an hypothesis.
- The condition in an experiment which contains the presence of the independent variable.
The subjects in an experiment who are allocated the independent variable which is changed or manipulated in order to observe its effects on their behaviour or experience.
An unconscious expectation of the experimenter which may influence their observations of data.
Occurs when the unconscious expectations, personal characteristics or treatment of the data by the experimenter may adversely affect the dependent variable which may bias the experimental results. This may occur when the experimental and control groups are treated differently.
Any potential independent variable that is of no direct interest to the researcher, but may have an effect on the dependent variable. The two types of extraneous variables are controlled and uncontrolled variables.
The applications of the conclusions based on the results obtained to other settings outside the study. Extending or applying the results for a sample more widely to the population from which the sample was drawn or another population
The notion that subjects who are aware that they are participants of an experiment may behave according to what they perceive to be the experimenter's expectations. The improved performance may be attributed to this factor, rather than the influence of the independent variable.
A testable predication that an independent variable(s) or treatment(s) will cause an effect on the dependent variable(s).
A research design in which subjects are randomly allocated to groups and it is assumed that relevant variables are balanced between the groups. This makes it equally likely for an individual to be in the experimental or control group.
Independent variable (IV)
The treatment variable (the factor or the characteristic) in an experiment that has been deliberately varied or systematically manipulated by the experimenter in order to measure whether it produced a change in the dependent variable, measured by a change in the subjects' behaviour or performance
Statistics that use mathematical procedures to measure and make judgments about how likely it is that the results are obtained in an experiment came about by chance
The process whereby an experimental subject is given all the necessary details in order to reach a decision to agree to being a part of an experiment. Such information should point out any potential risks that may be present in the research design.
A commitment by the researcher to the search for knowledge, to recognised principles for conducting research and in the honest and ethical conduct of research (including reporting)
Ensuring the fair distribution of benefits and burdens with the population of interest and well as for any research participant
A research design involving the placement of equivalent pairs of subjects into each group, matched on relevant characteristics such as gender, intelligence scores, age. Subjects are paired on variables which, if not controlled, may have a confounding effect on the research.
When all scores in a set of measurements are arranged in order, the median is the middle score within the set.
In a set of scores/measurements, the mode is the score that occurs most frequently. There may be more than one mode in any given set of scores.
Indicates that two variables share a relationship to one another which occurs in an opposite direction.' Thus, as one variable increases, the other variable decreases. For example, as the amount of study time increases, failure rate tends to decrease.
- A scientific research method in which the researchers endeavour to conceal their presence when recording their observations.
- A testable prediction that there is no evidence that the treatment has an effect. Thus, any difference between the experimental and control groups is due to chance. If one rejects the null hypothesis, they accept the experimental hypothesis. One cannot accept the null hypothesis
Data that has been gathered using systematic observation which is not influenced by any personal bias.
A scientific research method which involves watching and recording behaviour as it occurs in a clinical or naturalistic setting.
The interference of an observer's personal expectations, motives and prior experience which detracts from the accuracy their research.
The precise, comprehensive description of the concept to be measured in an experiment, and the procedures that will be utilised to measure that concept.
The expression of a hypothesis in terms of how the researcher will determine the presence and levels of the variables under investigation; that is, how the experimenter is going to put their hypothesis into operation.
Also called convenience sampling. Participants are selected from groups that are readily available
The potential impact on the results of the order in which an experimental task is completed by participants
The probability level which forms basis for deciding if results are statistically significant (not due to chance).
A scientific research the study; analysing the data; communicating the method in which the researcher watches and records the behaviour to be observed while engaging in the activity themselves in the hope of being mistaken by the subjects as a member of the activity
Process of assigning participants to different groups (or conditions in a research study)
A fake treatment often used in medical research in the form of sugar tablets or injections. It has no medical or pharmacological effects. It is often used as a control condition in experiments, to counter the effect of subjects knowing they have taken something.
Any observed change in functioning or behaviour that is 'caused' by a placebo, where there is a demonstrated difference between those taking the placebo treatment and those offered no treatment.
The entire group of individuals related to the problem of interest that the researcher is testing. A sample is drawn from the population
Indicates that two variables share a relationship to one another that occurs in the same direction. Thus, as one variable increases the other variable also tends to increase. For example, as the amount of exercise an individual performs increases, fitness level also tends to increase.
Factual or descriptive pieces of information about the qualities of the characteristics or behaviours being measured.
Numerical measures/values used to quantify, /describe the characteristics or behaviours being measured.
Random assignment / allocation
The allocation of subjects to different groups in an experiment ensuring that each subject has an equal chance of being selected in any of the groups to be utilised.
A form of allocating subjects from the population of interest to form part of the sample in such a manner that each member of the population has an equal chance to be selected. One method of doing this is using random number tables of selection. If the sample is of sufficient size, it is usually representative of the population.
the difference between the highest and lowest scores in a frequency distribution. The range is the simplest measure of variability.
One group undertakes both experimental conditions, the experimental condition and the control condition.
Respect for persons
Proper regard by the researcher for the welfare, rights, beliefs, perceptions, customs and cultural heritage of all individuals involved in research.
The method used to select subjects for a study. Types of sampling include random sampling and stratified sampling.
Scatter diagram (scattergram; scatterplot)
A graphical representation of the strength and the direction of the relationship between variables.
A series of orderly steps on clearly defined goals, objectivity and to obtain empirical evidence. are: preparing the study; conducting research reporting findings; and replicating or repeating the study.
Forms of gaining data which rely on spoken or written responses to questions posed by the researcher. Examples include interviews, surveys and questionnaires.
An experiment in which subjects are unaware of the experimental or control condition to which they have been assigned. This reduces the likelihood of the Hawthorne effect occurring.
A measure of the variability of scores in a distribution indicating the average difference between the scores and their mean.
Standardised instructions and procedures
Instructions and procedures used with all groups to make sure only the independent variable differs between them
When the likelihood of results (e.g. the difference in the mean scores for an experiment) being due to change factors is at an acceptably low level. In scientific research, a level of 0.05 significance is commonly used as a benchmark to gauge whether a difference obtained in the findings is truly due to the influence of the independent variable and not attributed to chance. A 0.05 significance level occurs when the probability of chance is 5 or fewer times in 100 repetitions of the research. Stricter probability values (p) of significance are sometimes employed, such as < 0.01 (less than 1 in 100); and p <0.001 (less than 1 in 1000).
The term used to indicate whether the results obtained in an experiment do not occur by chance and may therefore be the result to other variables.
A method of subject selection used to attempt to prevent biases by making the sample more representative of the population. It involves identifying some of the factors (strata) present in the population such as age, sex, or income level and then selecting a separate sample from each stratum in the same proportions.
Stratified random sampling
Sampling technique in which the population as a whole is divided into parts or 'strata' and each stratum has participants drawn from it.
Data obtained by self-report measures in which subjects give verbal or written responses to a series of research questions.
A mathematical procedure that involves a comparison of the means of two groups or treatment conditions to establish statistical significance.
Test of significance
A statistical test used to determine whether the mean scores of two groups differ significantly.
Those variables that have influenced the result as their presence was not accounted for (and removed) in the experimental method. Uncontrolled variables which cause a change in the value of the dependent variable are termed 'confounding variables'.
A factor pertaining to the property of an individual or object that can alter in amount or kind and can be measured.
Where subjects become a part of an experiment because they choose to do so. This choice is often based on being provided with some information as to the purposes, nature and procedures involved in the research design
The right of experimental subjects to remove themselves from the research situation at any point they decide (such as when the experiment is seen by the subjects as causing too much personal discomfort or distress).
The researchers responsibility to maximize the potential benefits of research and minimise the risks of harm or discomfort to all research participants
An in-depth study of some particular behaviour or phenomenon of interest in a particular individual, group or situation.
Examples of Secondary Authority
Legal Dictionaries, Treatises, Practice Guides, Form Books, Horn Books, Digests, Restatements, Legal Encyclopedias, Legal Periodicals, American Law Reports
It is 1 volume, and used for instructional puposes only. It's intent is to give you a general overview of the law. Not something you can use for research.
3 Legal Encyclopedias
American Jurisprudence 2nd Edition, Texas Jurisprudence 3rd edition & Corpus Juris Secundum
Types of Primary Authority
Case Opinions, Statutes, Codes, Agency Regulations, Constitutions, Ordinances, Treaties
There are 6 reporters
United States Reporters, Supreme Court Reporter, United States Supreme Court Reports, Federal Reporter, Federal Supplement, South Western Reporter
3 Supreme Court Reporters
Untied States Reports, Supreme Court Reporter, United States Supreme Court Reports
Doctrine of Precedent
doctrine that requires a court to follow the law established in a prior decision, unless good cause exists to change it
In order to determine when a court will have to follow something or not, you break it down into
The 4 Patterns are
The case and the court are in the same jurisdiction, One state does not have to follow what aother state did, Does state court have to follow a federal case, does federal court have to follow a state case
The case and the court are in the same jurisdiction
ask yourself if the case came from a higher court, if yes, you must follow.
Two different states, do not have to follow what each other says
Exceptions: Conflicts of Law or Full Faith and Credit
Does state court have to follow a federal case
generally no Exceptions: when there is a federal question (involves us Constitution)
Does a federal court have to follow a state case
generally no Exceptions: When they are required to interpret state law
Concurring Opinion is written by?
written by a person that agrees with the result, but for different reasons
ways laws can change
legislature can amend existing statutes or enact a new statute, court can apply its own interpretation to an existing statute or they can make law where there is no statute, supreme court can declare something unconstitutional
Where the results of an experiment are not disclosed to other participants or the participants' details remain anonymous when reporting on the experiment
A variable that is uncontrolled and allowed to change together with the IV, thereby having an unwanted effect on the DV
The group of participants that is not exposed to the IV providing a standard against which the experimenter can compare the performance of the experimental group
A group that is selected for an investigation from a population that is first encountered when sampling
Where the experimenter informs the participant of the purpose of the investigation at the conclusion of the research, including correcting any mistaken beliefs
A variable which shows any effects of the IV; the observed or measured response of the participants
Used to analyse, summarise, organise and describe important features of data so they can be further interpreted
An experimental procedure where both the experimenter and participant are unaware of the experimental conditions
A research methods used to test a hypothesis under controlled conditions in order to measure effects of an IV on a DV
When the experimenter's personal characteristics, actions or treatment of data affect the accuracy of results
An experiment's specific procedures for data collection, particularly the types of groups used - independent groups, matched participants & repeated measures
Any variable other than the IV that can cause change in the DV and therefore affect results in an unwanted way
Applying the results for a sample more widely to the population from which the sample was drawn
If participants are aware they are part of an experimental group they may simply improve because of that fact
A prediction of how the variables being studied will be manipulated, observed and measured as well as the population from which the sample was taken
Independent Groups Design
An experimental design in which each participant is randomly allocated to one of two or more entirely separate groups
A variable which is manipulated or varied by the experimenter in order to measure its effect on the DV
Statistics used to make judgements about whether the results for a sample would be the same for the population - how likely the results occurred by chance
Participants are made aware of the nature and purpose of the investigation beforehand and usually involves signed a consent form
Matched Participants Design
An experimental design that involves selection of pairs of participants who are similar in a characteristic that can influence the DV, then allocating each member of the pair to a different group
A predicted where there is no relationship between variable being studied - it is made to be disproved
A probability value that shows the statistical level at which chance is likely to have operated on the results obtained from research
When a participant's response is changed by their belief that they are receiving some kind of experimental treatment as opposed to change caused by the actual experimental treatment
Relationship between two variables in which a high rank on one is accompanied by a high rank on the other
A procedure for assigning participants to the various groups in an experiment which ensures that participants have an equal chance of selection to each group
The procedure for selecting a group of participants from a population that ensures each member has an equal chance of being chosen
Repeated Measures Design
An experimental design which uses the same participants in both the experimental and control groups
The selected group must represent the individual differences that exist in the population.
A study group which is selected from the population for allocation to the experimental and control groups
A series of orderly steps which are followed in conducting and reporting scientific research
A procedure in an experiment to ensure participants are not aware of the group to which they have been allocated
When the likelihood of results being due to chance is at an acceptably low level (p<0.05)
A procedure that involves diving the population to be sampled into distinct groups (or strata) then selecting a sample from each stratum
Participants are not placed under any pressure or coercion to participate in the investigation
The experimenter informs the participants that they are free to participate, decline or withdraw from the research at any time without reason should they wish to do so
hypothesis that states there is no difference between two or more sets of data making it opposite of the research hypothesis
procedure in which info that could introduce bias the result is withheld from participants, but experimenter will be in full possession of facts
confounding of variables
when two variables are linked together in a way that makes it difficult to sort out their specific effects.
researchers takes subjects & conditions as they naturally occur, with little if any control over what happens.
people of different ages are compared to one another at a single point in time
research in which the same people are re-studied and re-tested over a long period
if you take the same test 2x's & you get the same results it shows ______ reliability
alternate form reliability
A type of reliability, where different versions of same instrument are used and scores are compared
split half reliability
A test is divided into 2 halves and scores on the halves are compared to see if test is consistent within itself. Ex. compare odds & evens
More than one individual scores same test, regardless of who rates test - scores should be the same for _____ reliability
Extent to which scores suggest that a test is actually measuring an ABSTRACT theoretical idea (such as anxiety, personality, introversion, etc.).
form of validity in which a psychological measure is able to predict some future behavior or is meaningfully related to some other measure
measures whether a test looks like it tests what it is supposed to test as determined by a quick look or evaluation by a non expert
data of categories only. Data cannot be arranged in an ordering scheme. (Gender, Race, Religion)
data exists in categories that are ordered but differences cannot be determined or they are meaningless. (Example: 1st, 2nd, 3rd)
differences between values can be found, but is NO absolute ZERO. Examples: temperature F, time
A study of the procedures that different historians use in their research; also a study of the changing revisions and interpretations of the past.
Qualitative procedures that are used to develop detailed concepts or conditional propositions for situations; also, summaries of facts.
Ex post facto research
Research that investigates events that have already occurred and implies a cause-and-effect relationship from the results.
A research plan in which each step depends on the results of the field data obtained in the previous step.
Refers to research that describes an existing or past phenomenon in quantitative terms.
Qualitative research that examines a bounded system over time in detail, employing multiple sources of data found in the setting.
Research that tests or refines theory; not designed to be applied immediately to practice.
studies undertaken by practitioners in schools that address an actual problem or issue in the school or classroom.
Using existing and more qualitative research that has to do with...archival research, reference books, computer databases, and online searches.
when the target audience is asked to read or view the material in draft form before it is mass-produced and distributed.
an anthropology approach to conduct research through observation of group behavior
random sample (aka probability sample)
everyone in the target audience (as defined by the researcher) has an equal or known chance of being selected for the survey.
i.e. mall-intercept interviews. NOT random at all. Different people are present at different times
research that is done by organizations who send out surveys w/ questions that use highly charged words that elicit an emotional reaction from the respondent
when companies use software programs to track and monitor a client's reputation almost on a daily basis
when respondents often choose answers they think are "politically correct" or what the sponsor wants to hear
(1) researchers have more control of who gets them. (2) large geographic areas can be covered economically. (3) less expensive to use a paper-base. (4) large #s of people can be reached at minimal cost
(1) feedback is immediate (2) more personal form of comm. (3) less intrusive than door-2-door. (4) response rate can be higher
omnibus surveys (piggyback survey)
when an organization "buys" 1 or 2 questions in a national survey conducted by a national polling firm
(1) large samples in short amount of time (2) more economical than mail or questionnaires (3) data can be analyzed continually
research that is good for probing attitudes and perceptions, assessing penetration of messages, and testing messages
research that involves polls and surveys using highly precise scientific sampling methods
correlation where as one variable increases, the other also increases, or as one decreases so does the other. Both variables move in same direction.
research project designed to discover degree to which two variables are related to each other
in a normal distribution it tells you how far a number is above or below mean in terms of standard deviations.
positive (right) skew
skewed distribution where data has many more scores toward the lower end of the distribution
negative (left) skew
skewed distribution with many more scores on the higher end of the distribution
statement that describes how to measure a particular variable or define a particular term specifically in a study
Assigning participants to experimental and control conditions by chance, thus minimizing preexisting differences between those assigned to different groups.
sample drawn in such a way that known subgroups within a population are represented in proportion to their numbers in general population
expectations by researcher that might influence results of experiment or its interpretation
statistical measure of strength of association between two variables ranging from -1.0 to 1.0
covers references to virtually all English-language nursing and allied health journals, as well as to books, book chapters, dissertations, and selected conference proceedings
critical summary of research on topic, often prepared to put research problem in context or to summarize existing evidence
developed by US National Library of Medicine and is widely recognized as premier source for bibliographic coverage of biomedical literature; covers about 5,000 medical, nursing, and health journals published in about 70 countries and contains more than 16 million records dating back to mid 1960s; abstracts of reviews from Cochrane Collaboration are also available
first hand reports of facts or findings; in research, original report prepared by investigator who conducted study
second hand accounts of events or facts; in research, description of study prepared by someone other than original researcher
population of ppl available for particular study--often nonrandom subset of target population
form of sampling in which large groupings ("clusters") are selected first (eg nursing schools), with successive subsampling of smaller units (eg nursing students)
recruitment of all ppl from accessible population who meet eligibility criteria over specific time interval or for specified sample size
collection of qualitative data to point where sense of closure is attained because new data yield redundant info
criteria designating specific attributes of target population, by which ppl are selected for inclusion in study
maximum variation sampling
sampling approach used by qualitative researchers involving purposeful selection of cases with wide range of variation
selection of sampling units (eg ppl) from population using nonrandom procedures (eg convenience and quota sampling)
bias that can result when nonrandom subset of ppl invited to participate in study decline to participate
entire set of individuals or objects having some common characteristics (eg all RNs in New York); sometimes called universe
procedure for estimating either needed sample size for study or likelihood of committing Type II error
selection of sampling units (eg participants) from population using random procedures (eg simple random sampling)
nonprobability sampling method in which researcher selects participants based on personal judgment about who will be most informative; also called judgmental sampling
nonrandom sampling method in which "quotas" for certain sample characteristics are established to increase representativeness of sample
rate of participation in study, calculated by dividing number of some individuals to respond to items in characteristic ways (eg always agreeing) independently of item content
number of subjects in sample, major issue in conducting and evaluating quantitative research
distortions that arise when sample is not representative of population from which it was drawn
fluctuation of value of statistic from one sample to another drawn from one sample to another drawn from same population
simple random sampling
basic probability sampling involving selection of sample members from sampling frame through completely random procedures
selection of participants through referrals from earlier participants; also called network sampling
stratified random sampling
random selection of study participants from two or more strata of population independently
selection of sample members such that every kth (every 10th) person or element in sampling frame is chosen
entire population in which researcher is interested and to which he or she would like to generalize study results
in qualitative studies, selection of sample members based on emerging findings to ensure adequate representation of important theoretical categories
A property or variable for which the units are classified into just one of two categories
A statement asserting that specific variation in one property results in or causes specific variation in the property we are seeking to explain.
Variation in the independent property tends to cause directly or indirectly variation in the dependent variable
Books, publications, or journals with regular research; the primary source of explanations for more empirical research
A detailed discussion of how your research fits into the existing body of research on the subject
The retesting of hypotheses to see whether they are confirmed with different unit of analysis (justified)
It must yield the same results in the same circumstances the same way, regardless of who does the measuring
question with the high number always indicating that more of the property being measured is present
Indicators of central tendency
reflect the middle, central, or most common value in a distribution: mode, mean, and median
Indicators of dispersion
indicates the extent to which the values of the units are spread out or concentrated together: variation and standard deviation
computed by finding the difference from each value and the mean for category; then squaring and averaging those differences
the cases are distributed more or less evenly across the range of categories, may have no modal areas
mean is lower than the median; outlying cases are lower than the midpoint of the distribution
mean is greater than the median; the outlying cases are higher than the midpoint of the distribution
a subgroup of the theoretical population that has some identifying characteristics in common
if the independent property is measured for different units at a given point in time then the units that differ with regard to the independent variable will tend to differ in a specified manner with respect to the dependent
if the independent property is measured for different point in time then the units that differ with regard to the independent variable will tend to differ in a specified manner with respect to the dependent
A research procedure that uses statistical techniques to synthesize the results of prior independently conducted studies.
Refers to a study that combines qualitative and quantitative techniques and/or data anaylsis within different phases of the research process.
A form of historical research in which individuals' spoken words and testimonies about the past are recorded.
a type of research that refers to in-depth study using face-to-face or observation techniques to collect data from people in their natural settings.
A research paradigm in which objective data are gathered and analyzed numerically.
A study that duplicates the findings of a prior study using different participants, settings, or techniques.
The use of a questionnaire or interview to assess the current opinions, beliefs, and attitudes of members of a known population.
a document containing questions and other types of items designed to solicit information appropriate for analysis. Used primarily in survey research but also in experiments, field research, and other modes of observation
questions for which the respondent is asked to provide his or her own answers. In-depth qualitative interviewing relies almost exclusively on open-ended
survey questions in which the respondent is asked to select an answer from among a list provided by the researcher. These are popular in survey research because they provide a greater uniformity of responses and are more easily processed
that quality of a measurement device that tends to result in a misprepresentation, in a particular direction, of what is being measured
A survey question intended for only some respondents, determined by their responses to some other question. p279 for example
the number of people participating in a survey divided by the number selected in the sample, in the form of a percentage. Also called Completion Rate or, in self-administered surveys, the Return Rate: the percentage of questionnaires sent out that are returned.
a data-callection encounter in which one person asks questions of another. May be conducted face-to-face or bu telephone.
a technique employed in interviewing to solicit a more complete answer to a question. It is a nondirective phrase or question used to encourage a respondent to elaborate on an answer. Ex. "Anything more?" and "How is that?"
a form of research in which the data collected and processed by one researcher are reanalyzed by another. Especially appropriate in the case of survey data.
idea that a test shoud appear to any person to be a test of what it is supposed to test
a test should sample the range of the behaviour that is represented by the theoretical concept being tested
idea that a test should correlate with other measures of the same theoretical construct
a test that the measurements actually measure the constructs they are designed to measure but no others
variability in the dependent variable that is not associated with the dependent variable
similarities and differences. classifies objects or events into categories same event get same number
ranks objects/events inorder of their magnitude. the position of the numbers on the scale must represent the rank order of the psychological attributes of the object
one in which the differences between the numbers on the scale are meaningful. equal differences between the numbers on the scale must represent equal differences between the event or objects
one that has a meaningful 0 point as well as meaningful differences btw the numbers on the scale. the ratios btw the numbers on the scale must represent the ratios btw the evnts/objects
extent to which a study provides evidence of a cause-effect relationship btw the independent and dependent variable
aspect of an experiement designed to make certain that varible have changed in the way that was intended
how well the findings of an experiment generalize to other situatons or populations; different subjects, settings, times, etc
extent to which data are shown to be he result of cause-effect relationships rather than accident
threats to validity
events outside the laboratory, maturation, effects of testing, regression effect, selection, mortality
threats to construct validity
loose connection between the theory and method, ambiguous effect of independent variable
cause and effect relationships
They are determined by manipulating the independant variable, measuring the dependant variable, and controlling all other variables
within subjects design
Research done where conditions are tested within individual subjects and each subject recieves every manipulation
Research that looks at variables by comparing different groups of scores and uses less manipulation of variables than experimental research
Research with a more reasonable level of control in comparison to experimental and may even require no manipulation at all
It asks if the measurement procedures actually measure what you intend to measure
They make the independant variable and dependant variable relationship unclear
They are factors which make changes in the dependant variable hard to observe and also cause increased measurement error and more noise in the data
A scale which records the amount of time between an instruction and when the behaviour is atually performed
Is the result of the independant variable being manipulated and cannot be separtated from the results
answer different question sets based on prior answers ex drinking portion on a health questionnaire
population numerical composition is maintained. data collected haphardly. ex study males in caf
groupings from a larger population. ex. 1/10 of student of every class... not 1/10 of every class
attempts to descrie variables. looks at variables as they exist naturally, identify correlations btw variables by comparing
Quasi- experimental research
aim to define cause-effect relationships, fails to manipulate independent variable, often compares pre-existing groups(factory in ottawa vs. one in toronto)
pre-test ppts on an important(potentially confounding) variable so that it can be controlled for
potential confounds that can't be easily removed so made as IV as a means of control
based on an extensionof theory, most common type, ex if this theory is correct the following should happen
the same experiment is repeated, uncommon, only happens if systematic replication fails
categories defined so that membership to one rules out membership to other. ex cant be both graduate and under grad student
a form of cluster sampling in whcih clisters are further broken down by taking samples from each cluster
changes in a subjects performance resulting fromthe postion in which a condition appears in an experiment
changes in a subjects performance resulting from interactions among the conditions themselves
controlling for order and sequence effects by arranging that subjects experience the various conditions in differeent orders
control procedure in wich the order of conditions is randomized but with each condition being presented once before any condition is repeated
reverse counter balancing
method of control in which conditions are presented in order the first time and then in reverse order
control procedure in which each subject experiences each condition in a different order from other subjects
multiple conditions design
compare several variables/treatments for effectiveness, not usually yes/no questions, subjects experience all conditions
one group posttest only design
research design that measures the behaviour of a single group of subjects after they are given a treatment, threats to validity uncontrollable
one group pretest postest design
measures the behavious of a single group of subjects both before and after treatment, know the behavious change, may be considered a quasi experiment
2 phase experimental design consisting of a pre-treatment baseline condition (A) followed by a treatment condition (B),
3-phase design consisting of initial baseline phase (A) until steady state (B) implemented until behavior has changed and steady state, return to baseline (A) by withdrawing IV (B)",
A-B-A design with addition of second intervention phase to see if initial treatment effects are replicated
Design in which baseline period is followed by a second phase in which 2 IVs are administered, and the more effective IV is continues to phase 3
2 phase experimental design consisting of a pre-treatment baseline condition (A) followed by a treatment condition (B),
3-phase design consisting of initial baseline phase (A) until steady state (B) implemented until behavior has changed and steady state, return to baseline (A) by withdrawing IV (B)
A-B-A design with addition of second intervention phase to see if initial treatment effects are replicated,
Condition of an experiment in which IV is not present; data obtained during baseline is basis for determining effects of IV.
Changing Criterion Design
Design in which baseline is followed by phases of successive and gradually changing criteria
Measurement conducted so that all instances of the response class are detected during the observation period
Any form of measurement in which some instances of the response class may not be detected
The variable in an experiment measured to determine if it changes as a result of manipulations of the IV
Documents individual occurrences of a response or stimulus during an observation period
Comparison of some measure of the DV under 2 or more different conditions in which the IV differs from one condition to another
When a predictable change in the DV can be produced by the systematic manipulation of the IV
Type and sequence of conditions in a study so that comparisons of the effects of the presence and absence of the IV can be made
When a change in the DV is produced by systematic manipulations of the IV and the change unlidely to be result of other extraneous variables
The variable that is systematically manipulated to see whether changes in the IV produce reliable changes in the DV
Inter observer agreement
When 2 or more observers report the same observed values after measuring the same event
When the level of responding in a previous phase cannot be reproduced even thought conditions are the same
Partial Interval Recording
Observation is divided into brief time intervals; observer records whether target behavior occurs at ANY TIME during interval
Measuring a behavior after it occurred by measuring it's effects on the environment
Repeating of experiments to determine the reliability and usefulness of findings and determine mistakes
Design in which to verify the effect of the IV by reversing responding to a level in a previous level
The extent to which target behaviors are socially appropriate and the extent to which significant changes are produced
Extent to which data from measurement are relevant to the target behavior and to the reason for measuring it
Design in which an effective treatment is withdrawn to promote maintenance of behavior
least squares method
a method of calculating the line of best fit using the distance each point is from the line of best fit
Pearson product-moment correlation coefficient
a measure of how well the regression equation fits the data
If we use knowledge of SAT scores to predict his or her GPA. wHAT IS THE PREdicTOR AND WHAT IS THE CRITERION?
sat IS PREDICTOR AND GPA IS CRITERION
If we can claim to account for .65 of the vvariance in Y scores by knowing a relationship, it means that?
We are on average, 65% more accurate at predicting Y' scores than we would be if we did not know the relationship.
In general, the greater the proportion of variance accounted for...
the more accurately we can predict the behaviour
If heterodasticity is present Sy' will be?
greater than the actual average error in predictions of Y for some scores and less than the actual average error for other X scores
The regression line can be thought of as a series of points representing?
all the possible Y' values associated with all possible X scores
Standard error of the mean is defined as?
Average spread of actual Y scores around the predicted Y scores
Linear regression is defined as the procedure for determining?
the best-fitting straight line in a linear relationship
When we square hte correlation coefficient to produce r2, the result is equal to the?
proportion of variance accounted for
The Y-intercept of a line is the?
value of Y at the point where the regression line crosses the Y axis
Suppose you have several different predictor variables and one criterion variable. all your variables are measured using interval or rations scales. What is the appropriate statistical test to use?
We should always draw a scatterplot of the data when we compute a correlation because hte scatterplot allows us to?
see the nature of the relationship between the two variables
When your scale correlates with other procedures or scales that are valid, it has__________ validity ?
When your scale does not correlate with other unrelated procedures or scales it has ________validity?
When the relationship between two variables is high (for example, r=.98) the variability in the Ys at each X is ____________ realtive to the overall variability of Y scores in the sample.
In general, a positive linear relationship means that?
as the values of one variable increase, there is a tendency for the values of the other variable to also increase.
Suppose you find a restriction of range in your study of IQ scores and school achievement at school. Restricting the range is likely to _____ the correlation coefficient.
decrease the size of
Whe consistency of participants responses to the same test at two different times determines?
The consistency of participant response on different versions of the same test determines?
If we plot a scatterplot, and the data points form a shape that appears to be random dots and is far from forming a slanted straight line as possible, the correlation for the data is?
0.0: there is no relationship
THe defining formula for the Pearson correlation coefficient shows that it is the?
average correspondence of paired X and Y z-scores
What procedure would be used to find out whether there is a relationship between SAT scores and GPA?
The Pearson correlation coefficient
In general a positive relaitonship means that?
As one variable increases the other variable also increases
We should always draw a scatterplot of the data when we compute a correlation because it alows us to see?
the nature of the relationship between the two variables
As the variability--differences--in Y scores at each X become larger, the relationship does what?
becomes weaker and results in a smaller correlation coefficient
The larger the correlation coeficient (whether pos. or neg.), the stronger the relationship. Why?
The less the Ys are spread out at each X and the closer the data come to forming a straight line
What is another word for the degree of efficeincy in a relationship?
coefficient although it DOES NOT directly measure units of consistency
Define the purpose of computing a correlation coefficient.
Statistical technique for demonstrating the reliability and the validity of a measurement procedure in any experiment or correlational design.
What are the types of reliability that a correlation coefficient is used to show?
test-retest, inter-rater, split-half
Test in which participants receive the same score when tested at different times
Procedure is valid because it looks valid/Extent to which a measurement procedure appears to measure what it was intended to measure
Extent to which scores obtained from one procedure are positively correlated with scores obtained from another procedure that is already accepted
Extent to which scores obtained from one procedure are not correlated with scores from another procedure that measures OTHER variables or constructs.
Define the Pearson correlation coefficient
Corelation coeffieccient that describes the strength and type of a linear relationship between interval and ratio variables, symbolized by r.
Define the Spearman Rank order coefficient
The correlation coefficient that describes the linear relationship between pairs of ranked scores (ex: any two ordinal variables OR tied rank variables, symbolized by Rs
Tied rank variables
occcurs when two aprticipants receive the same ranking score in SPearman's rank coefficient, resolved by averaging the score and assigning it to both participant to correlate their scores.
Point biserial correlation coefficient
Describes the linear relationship between the scores from one continuous variable and one dichotomous variable (ex: correlating male/female with interval scores from a personality test).Can be used for one continuous interval or ration and one dichotomous, symbol is Rpb.
How does a restricted range affect a correlation coefficient?
reduces the accuracy, producing a smaller coefficient than if hte range were not restricted and leads to an underestimate of the degree of association between the two variables. Avoiding this increases power.
Why is the correlation coefficient important?
It is one number that allows us to envision and summarize the important information in a scatterplot, in terms of it's strength and direction.
The smaller the absolute value of the coefficient, the greater the ?
variability of the Ys at each X, the vertical width of the scatterplot, and the less accurately Y scores can be predicted from X
How can the power of a correlational design be increased?
Minimizing error variance and avoiding a restricted range, so that thelargest possible coefficient is obtained.
If it passes through the proper inferential procedure, a sample correlation coefficient is used to estimate what?
the corresponding population correlation coefficient: r=p,Rs estimates Ps, Rpb estimates Ppb.
Define linear regression
THe statistical procedure for using a relationship to predict scores aka the statistic that summarizes the linear relationship.It produces the line that summarzes the relationship
What does the symbol Y' stand for
a predicted Y score. Our best prediction of the Y score at a corresponding X
Define regression line
straight line that summarizes the linear relationship in a scatterplot by,on average, passing through the center of the Y scores at each X and it consists of the predicted Y score-the Y'-for every possbile X
What is the importance of linear regression?
It is used to predict a individual's unknown Y score based on his/her X score from a correlated variable. Usually more external validity and more accurate description of the relationship.USed to predict unknown Y scores based on X scores from correlated variable.
Linear regression equation [(b)(x) + a]
equation that creates the straight line by producing a value of Y' at each X, define sthe line that summarzies the relationship. Describes it's slope and Y intercept.
SEE (Sy) is acronym for
Standard error of estimate which is the standardized difference between predicted Y' and actual Y scores
How do you calculate proportion of variance accounted for?
r2 which is also known as "coefficient of determination"
When r=0, the standard erro of the estimate is at it's max. and that is equal to?
the standard deviation of all Y scores in the sample (Sy)
What does the equation r2 aka coefficient of determination aka proortion of variance indicate?
How important the realtionship is by comparing amount of error obtained using the regression equation for XY to errors without the regression equation for XY
what does Sy2 refer too?
Describes the error variance when using regressinon to predict Y scores, measures error in prediction.
Sr' definitional formula/average error
subtract Y' from Y and square each deviation/divide by N then find hte square root of that to get the error of the estimate
proportion of variance
is the amount we reduce errors in predicting Y scores when we use the relationship, compared too if we did not. Equals r2
The differences (and error) between Y and Y' is also summarized by what?
the variance of the Y scores around Y' (S2y)
If there is a large R there is a week or strong relationship?
stronger the relationship and a small value of Sy and S2y, because the Y scores are closer to Y', thus the smaller difference between Y and Y'
An unequal spread of Y scores around the regression line (that is around the values of Y')
When there are few (2-3) categories to the dependent variable, one uses a percentage crosstable (calculated down, read across)
Comparisons of central tendency
4-5 categories of the DV, one uses a comparison of central tendency - a table showing the mean or median value of Y for each category of X
Indicates the strength and direction displayed in a table - (positive, negative) summarizes the findings of each table in a single number
the crosstables' showing of the number (N) of cases in each column (the number the percentages are based on) and perhaps each row
dealt with after comparisons of central tendency, not as easily understood to the reader, summarizes the strength and direction displayed in a table (phi, Somer's d, Tavb, Tauc, and Gamma)
the X and Y values are paired in such a way that knowing the X value of a unit is no help in predicting its Y value - statistically independent
used for summarizing bivariate (2*2) tables - it is a special case of correlation coefficient for interval variables calculated: (ad-bc)/√(a+b)(a+c)(c+d)(b+d)
Tests of significance
test that tell us how likely it is that an association as strongly supportive as the one observed in a sample would be found when no supportive association exists in the population (showing it's not by chance) - can tell the odds are very small
the distributions in samples are likely to be somewhat different from the distributions in the theoretical population (±4%)
Level of statistical significance
it is reported as a proportion indicating the maximum probability of incorrectly finding that an association exists (.05 level = 5 chances out of 100)
Known sampling distribution
statisticians have already determined the likelihood of getting each value when samples with given characteristics are drawn from a population in which there is no association (X2, t, z, and F)
any test of significance in which the direction of association is hypothesized in advance, and only an association in that direction can be statistically significant - indicates the probability that an association as strongly supportive of the hypothesis would have occurred by chance in a sample drawn from a population in which there was no association - test hypotheses
a test of significance in which an association in either direction can be statistically significant - test exploratory research
Chi square x2
use for percentage difference, tables with 2*2, and difference between medians - values indicate how unlikely it is that the observed sample results came from a theoretical population with no association between X and Y
Degrees of freedom (df)
reflect the number of cells in the table: (number of rows - 1)(number of columns - 1)
Sum of Squares Within (SSw)
gained when calculated the variance - it is the sum of the squared deviations for each X category
Sum of Squares Between (SSb)
calculated from the squared deviations of the means for each X category about the mean for the whole sample - N1(mean - mean for entire sample)2 + N2 (mean - mean for the entire sample)2
Asymptotic standard error
a measure similar to standard deviation , measures how much dispersion one would expect in correlation coefficients - no association
required for associations to be proved causal, controls for the effects that other variables have on the association
variables caused by the IV, they intervene in a causal sequence between the IV and DV
research in which the scientists determine the amount or level of the independent variable to which each unit is exposed (rarely used)
summarizes the relationship of several things - measures the extent to which the Y values of units can be estimated from the X values of those units by using an equation of the type: Y′ = a + bX - a = intercept value / X = variable / b = coefficient slope (the explanation)
what r measures the extent of between X and Y (dots closer to the line - higher number / farther dots - low number)
Regression coefficient (slope)
the one that multiplies times the X value , the amount by which Y is estimated to increase/decrease for each increase of 1 in the value of X)
the constant that is added to or subtracted from the multiple of X - the point where the regression line crosses the Y axis - it is the value if X were zero, Y would be it (a)
the difference between a Y value estimated from the regression equation and the actual Y value for each unit - the lower the values of r, the larger the residuals will be
R2 and adjusted r2
virtually the same if the sample is 50 or larger, tells us how much of the variance in Y in the sample was explained by X (same as proportion of explained variance)
a complete or selective list of works complied upon some common principle, as authorship, or subject
searching the web or databases using limiting or expanding Boolean terms, including AND, NOT or OR
in citation entries, the first line flush with the margin, each consecutive line is indented 1/2 inch
information directly from someone involved in an event (diaries, lab results, newspaper reports from the time)
contains the work of experts & academics in a given field, circulated to a limited, expert audience
using material from a source in your own words & sentence structures, points are in the order the original author presents them
a significantly shortened version of source material that captures main ideas in your own words
phrases indicating whether the writer of the paper is speaking, or if they are using outside source materal
MLA in text- citation typically consisting of the source author's name & a pg. no. or in the case of no author, a key word from the title
non-probability design in which you use the most readily available persons as subjects. May use snowball sampling. Most commonly used because its convenient and least costly.
non-probability design in which you identify a significant extraneous variable and use accidental sampling to select a predetermined number of subjects from each strata
non-probability design in which you handpick subjects on the basis of personal judgment about their representativeness.
Probability sampling designs
simple random sampling, stratified random sampling, cluster sampling, systematic sampling
Simple random sampling
probability design in which a table of random numbers is used to draw a sample from the population.
Stratified random sampling
probability design in which you identify a significant extraneous variable and randomly select a predetermined number of subjects from each stratum.
probability design in which large groupings or clusters are randomly selected first with successive random sub-sampling of smaller units. Most commonly used for large-scale surveys because it is more economical and practical. Contains more sampling errors
probability design in which you select the every Kth case from a list. It may not be random if the list is arranged so certain types of elements are listed at particular intervals.
equation to determine the sampling interval width (k)
estimated number of people in population / desired sample size
data collection methods
questionnaires (open structured vs close-ended structured), Interviews, diaries, scales (likert, guttman, semantic differential, and visual analog)
data collection method which is low cost, little time, anonymous, has no interviewer bias, can not clarify, has a low response rate, and has little control over subject.
data collection method which has a higher cost, takes more time, is not anonymous, has interviewer bias, has a high response rate, can control subjects, and can clarify questions.
Questions that are unstructured, have no predetermined response, provides a depth of response, takes a long time to administer, and is hard to analyze
Dichotomous question (yes or no), multiple-choice question, "cafeteria" question, rank ordered, forced-choice, and rating questions.
Interview that is conversational but meant to determine the subjects' perception of phenomenon. It is taped, lasts several hours, and latter transcribed.
interview that is an encouraged conversation with a set of questions or a topic guide
a narrative self disclosure about ideas and chronological experience regarding a theme
Think about method
subjects audio-record problem solving and decisions being made over a period of time
Critical Incidents technique
asking subjects to describe critical incidents related to behavior being studied
The most commonly used scale that is composed of a series of favorable and unfavorable statements that the subject indicated their degree of agreement or disagreement.
Scale in which items are arranged in a hierarchy. Subject picks a "yes or agree" to all items lower and "no or disagree" to all items higher. often used to test child development.
Semantic Differential scale
subjects rate concepts on a series of 7 or 8 point bipolar rating scales.
Visual Analog scale
scale that rates the amount of sensation experienced on a 100mm long line. Score is derived by measuring distance from end of the line to the subjects mark.
Maximum variation sampling
Purposefully handpicking subjects with a wide variation on the dimension of interest
Extreme/deviant case sampling
purposefully selecting subjects that are the most unusual or extreme with regard to the dimension of interest
Typical case sampling
purposefully selecting subjects who are typical or average with regard to the dimension of interest
The subjects tendency to guess when in doubt about the answer to an item. Control by instructing to or not to guess or by using a correction formula
Subjects tendency to respond in socially desirable ways or consistent with social mores. Control with anonymity
Tendency to consistently agree or disagree with attitudinal statements. control by constructing scales so some items are phrased negative and some are positive.
Enhancement of contrast effect, central tendency, assimilatory, halo effect, error of severity
Distorting observations in the direction of identity with previous input or data (looking for regularities)
Projective data collection techniques
Pictorial (thematic apperception test (TAT), Rorschah Test, projective cartoon), verbal (word association, sentence completion), expressive (playing with dolls, drawing, painting, role playing).
Thematic apperception test (TAT)
subject is given twenty cards that contain pictures and are asked to make up a story about each picture.
subjects are given cards containing pictures of ink blots and are asked to describe the picture
Subject is told a series of neutral and emotionally laden words and asked to respond to each word with the first thing that comes to mind.
Subjects are given a series of incomplete sentences about an object or event and are asked to complete the sentences
pros/cons of projective techniques
less susceptible to faking, easy to build rapport with subjects, useful with children, questionable reliability and validity
data collection method in which the subject is given 50-120 cards with statements on them and are told to sort them into categorical piles.
Data collection method which entails collecting data that has already been gathered (health records, historical research, secondary analysis (data from previous study), and meta-analysis (combining data from several studies)).
include who, what, where, and when to make a good representation of the target population.
a complete or selective list of works compiled upon some common principle, as authorship, or subject
searching the web or databases using limiting or expanding boolean terms including: AND OR and NOT
in citation entries, the first line flush with the margin, each consecutive line is indented 1/2 inch
MLA in text citation typically consisting of the source author's name and a page number or in the case of no author, a key word from the title
contains the work of experts and academics in a gived field, circulated to a limited, expert audience
using material from a source in your own words and sentence structures, points are in the order the original author presents them
a significantly shortened version of source material that captures main ideas in your own words
phrases indicating whether the writer of the paper is speaking, or if they are using outside source material
characteristic that may take changing forms called values, eg variable gender: one value is male
variable with values that alter in form but not quantity eg gender, eye colour, grade of moxa
variable that can have unlimited number of possible values eg length, mass, area, temp
varibale that may only take on specicifc, discrete values eg number of children in a fam, gender, number patients attending a clinic each day
a complete set of individuals/objecfts/measurements having some common observable characteristic eg census that measures all sorts of variables
a subset of a population selected so that each member of the population has an equal opportunity of being selected, out of a hat
a number resulting in the manipulation of some data according to certain specified procedures eg mean age for students in class, add up all ages and divide by number of students
any characteristic of a population that is measureable eg mean age, gender split, number of individuals
mutually exclusive events
events that cannot occur simultaneously eg being dead and alive at same time
placing values for a variable in order of magnitude to show the number of times each is score occurred eg number of visits 1 2 3 4 age 10 11 12 13
grouped frequency distribution
collapsing measuerment scale so scores assigned to mutually exclusive grouping intervals eg age group 10 to 20, 20 to 30 etc
any extraneous variable that changes systematically with the IV and competes with the IV as the effect of the change in the DV
the characteristic of an experiment that allows one to draw accurate inferences about the causal relationship between an independent and dependent variable
Post test-only design
experimental design that uses a test measure only after presentation of the IV
Differences in the type of subjects who make up each group in an experimental design; this situation occurs when participants elect which group they are to be assigned to or when participants who form the two groups are chosen from existing natural groups
the only difference between this and the posttest only is that this design gives a test prior to introducing the IV to ascertain that the groups were, in fact, equivalent at the beginning of the experiment
independent group designs
participants are randomly assigned to the various conditions so that each participates in only one group
the order of presenting the treatments effects the DV. Types of order effects: practice effects and fatigue effect, contrast effect. To deal with these effects: employ counterbalancing techniques or devise a procedure in which the interval between conditions is long enough to minimize the influence of the first condition on the second condition
is a deterioration in performance as the research participant becomes bored, tired, or distracted
occurs when the response to the second condition in the experiment is altered because the two conditions are contrasted to one another
all possible orders of presentation are included in the experiment; by counterbalancing, it is possible to determine the extent to which order is influencing the results; these principles can be extended to experiments with 3 or more groups
a technique to control for order effects without having all possible orders; a limited set of orders constructed to ensure that each condition appears at each ordinal position and each condition precedes and follows each condition one time
2 basic strategies of scientific research
Describe the relationship (descriptive designs & Correlational design), Explain the relationship (quasi-experimental designs & experimental design)
Goal of the experimental research
verify the existence of a cause and effect relationship between two variables
Why? Relationships between variables are complicated; cognitive biases for example
2 problems with variable relationships
directionality problem -does the first variable cause the second or does the second variable cause the first?
Third variable problem (alternative explanation)- sometimes we see relationships between variables that don't rule out alternative explanations where a third variable causes both
"A simple description of a relationship does not mean there is a cause and effect relationship" - prof.
establish cause and effect
Demonstrate a directional relationship between the variables; demonstrate that a change in one variable causes the change in the other variable. How? Manipulate one variable and measure the change in a second variable while controlling extraneous variables (any other variables within the situation we are studying)
Elements of an experiment
Independent variable (IV), Dependent variable (DV), Experimental Control, randomization
Independent variable (IV)
the causative variable, we think there is a cause because we have identified a correlational relationship can be manipulated (i.e., has levels)
What or who determines the levels of the IV?
experimenter - in true experimental design, the levels are selected by the experimenter in experimental designs in quasi-experimental designs, the levels are predetermined (can't change political affiliation or hair color, anything that has been set by nature or selected by the environment, we can't change)
Dependent variable (DV)
the changed variable - change in variable can be observed and/or measured change is brought about by the IV; doesn't occur in the absence of IV
you want to control for everything except for your independent variable; control for any or all procedures that limit the possibility that the observed change in the DV is caused by some other variable that the IV. This is accomplished through random assignments - but still can never guarantee this 100%. When we control the experiment well, we can say that the experiment has high internal validity
includes things like beliefs, characteristics,emotional characteristics, how much sleep they've had
What are two levels of IV
2 experimental groups: compare a standard level of treatment with other levels of treatments / Placebo (control) group & treatment group: have to make sure everything experiences the same thing - same treatment, etc
How do you avoid confounding variables / unconfound
evaluate and determine if they will actually confound to issue, keep them constant across conditions; match values across conditions, make them as identical as possible
Why is it important to make the manipulation as strong as possible?
maximizes the differences between the two groups, increases the chances the IV will be effective for a real world match
test has to be strong enough without being too difficult - ceiling and floor effects (best way to avoid these effects is to have multiple measures)
Solomon 4 group design
has 4 groups: 2 pretest/post-test & 2 post-test only; solves problem of pretest sensitization because it allows us to see if their was a pretest sensitization
use when a true experimental design can not be used because there are variables we can not change; group/condition has been assigned by factors other than the experimenter; has nonequivalent groups, static groups; used for single subject or program evaluation
studies change as a function of age; same group of people at time 1, 2, 3; downsides-mortality, funding, harder to generalize
Cross Sectional experiment
studies differences as a function of age; same time with different age groups; downsides-cohort effect
if you are collecting data over a period of time and something happens in the real world that affects the study by changing attitudes or behaviors
Types of manipulations
Straightforward: manipulate variables with instructions and stimulus presentations; Staged: staging events that occur during the experiment in order to manipulate the independent variable successfully
accomplice, person who appears to be another participant but is actually part of the manipulation
can be used to measure attitudes, liking for someone, etc; rating scales with descriptive anchors are most commonly used
Examples of physiological measures
galvanic skin response: measures general emotional arousal and anxiety, electromyogram: measures muscle tension and is frequently used as a measure of stress, electroencephalogram: measures electrical activity of the brain cells
allows researchers to scan areas of the brain while a participant performs a physical or cognitive task
the IV appears to have no effect only because participants quickly reach the max performance level
any feature of an experiment that might inform participants about the purpose of the study
experimenter bias/expectancy effects
experimenters are usually aware of the purpose of the study and thus may develop expectations about how participants should respond
independent groups design
a different group of participants will be assigned to each of the four conditions
single case experimental design
used to determine whether an experimental manipulation had an effect on a single research participant
in a single case design, the subject's behavior during a control period before introduction of the experimental manipulation
a single case design in which the treatment is introduced after a baseline period and is then withdrawn during a second baseline period; demonstrates 'reversibility'; helps show that the manipulation of the IV had an effect; called ABA design
multiple baseline design
the effectiveness of a treatment is demonstrated when a behavior changes only after the manipulation is introduced; to demonstrate the effectiveness of the treatment, change must be observed under multiple circumstances to rule out the possibility of extraneous variables
multiple baseline across behaviors
several different behaviors of a single subject are measured over time
research on programs that are proposed and implemented to achieve some positive effect on a group of individuals
any changes that occur systematically over time can cause changes from the pre to post tests
a combination of the cross-sectional and longitudinal design to study developmental research questions
a reliability coefficient determined by the correlation between scores on a measure given at one time with scores on the same measure given at a later time; assessed by measuring the same individuals at two points in time
internal consistency reliability
the assessment of reliability using responses at only one point in time
an internal consistency indicator of reliability; the researcher calculates the correlation of each item with every other item
appeal to authority
argued that a statement is correct because the statement is made by a source that is regarded as authoritative
empirical evidence that supports and is properly documented in accordance with scientific method such as is applicable to the particular field of inquiry
untested, unreferenced statement, conclusion is unreliable; it may not be untrue, but it doesn't follow from the "evidence", eg evidence can be anecdotal in both senses: "Goat yogurt prolongs life: I heard that a man in a mountain village who ate only yogurt lived to 120."
hypothetical abstract construct
A hypothesis is a proposed explanation for an observable phenomenon, hypothetical: "being assumed to exist as an immediate consequence of a hypothesis,"
the extent to which a concept, conclusion or measurement is well-founded and corresponds accurately to the real world
abstract concept made concrete
Concrete thinking involves facts and descriptions about everyday, tangible objects, while abstract (formal operational) thinking involves a mental process
an indicator of reliability that examines the agreement of observations made by two or more raters
the degree to which a measurement device accurately measures the theoretical construct it is designed to measure
assesses the relationship between scores on the measures and an specified outcome
the construct validity is measured by examining the ability of the measure to predict a future behavior
the extent to which scores on the measure are related to scores on other measures of the same or similar construct
examines the extent to which scores on the measure are not related to scores that measure some other unrelated construct
a descriptive method in which the experimenter observes people in natural settings/ natural social settings
a type of case study in which the life of an individual is analysed using psych theory
like Lori's coloring book article - examines the subjects and ideas in media/written documents
when someone goes down the line on a survey and selects one consistent answer every time
intentional or unintentional influence exerted by an interviewer in such a way that the actual or interpreted behavior of respondents is consistent with the interviewer's expectations
an interval of values within which there is a given level of confidence where the population value lies
stratified random sampling
ensures that the sample matches the important characteristics of the population
take participants any way you can get them; not that representative because they are volunteers
type of haphazard sampling conducted to obtain pre-determined types of individuals for the sample
similar to stratified too; the sample is chosen to reflect the numerical composition of various subgroups in the population; ie: if UAA is 60% men and 40% women, our sample of UAA students would be 40% women and 60% men too but otherwise randomish
the individuals or clusters of individuals who might actually be selected for inclusion in the sample
an individual's actual score without anything affecting it positively or negatively; can never get this score
3 types of archival research data
statistical records, survey archives, written and mass communications, documents
the extent to which a test samples the behavior that is of interest (such as a driving test that samples driving tasks).
predictive, discriminant and convergent/concurrent - the scores on similar types of measures come together and are similar
also called divergent, our scores would be different than on tests that measure different things; can discriminate our construct from all other types of constructs
numerical index that represents the relationship between two variables; -1.00 to +1.00; represented by r
2 components of the relationship between two variables
strength -represented by the absolute value of r (0 to 1); direction - positive or negative; represented by the sign of r; direct has a positive sign, indirect is negative (Wesalowski likes terms direct/indirect over pos/neg)
primary limitation of correlational research
can not assess cause and effect for the most part, can tell us if they are related - no control of extraneous variables, this limitation is referred to as the directionality problem and the thrid variable problem
can't say which variable causes the change in the other; either variable could be the explanation
third variable problem
third variable causes both sides of a relationship; heat increases ice cream eating and murder
(also applies to an interview) have a purpose/objective (big research question operationalized), short and sweet (solicit essential info only), directions are clear and explicit, include conditional information prior to key ideas (in directions), include transitions between sections, reliable, types of questions, vocabulary, questions short & concise (20 words or fewer), positive slant, consistent response formats within a section, edit questions, clear/specific/objective/forthright, avoid assumptions, avoid leading questions (suggest a right answer), avoid loaded questions (volatile, emotional), avoid double barreled (two questions at once), avoid insulting
types of questionnaire questions
open ended - advantages: get complete answers, reasoning, and unexpected information / disadvantages: hard to code, answers must be rated (categorized); closed ended - advantages: easy / disadvantage - simplistic answers, forced choices USE BOTH
population, sample, representative - sample needs to represent the population, probability and non-probability
use if accuracy if representativeness is very important; simple random sampling, systematic random sampling (every kth person), stratified random sampling, cluster sampling
use when representativeness is less important, test theoretical hypothesis; experimental designs, don't know who is going to show up to participate; the probability of the population being selected is usually not known because sampling is based on convenience; sample may not truly represent the population, may reduce external validity
amount of discrepancy between population's characteristics and sample's characteristics - random sampling error; smaller is better
an attempt to measure whether the independent variable manipulation has the intended effect on the participants
A design in which all levels of each independent variable are combined with all levels of the other independent variables. Allows investigation of the separate main effects and interactions of two or more independent variables.
simple main effects
examines mean differences at each level of the independent variable; the results are analyzed as if we had separate experiments at each level
any decrease in the accuracy of your measurement tool; when you are making observations, sometimes you have raters who get tired or bored
aka regression to the mean, extreme scores have the tendency to return to the mean; has to do with the idea that everyone/thing has a true score/innate ability, it's hard to measure because of confounds
To avoid or mitigate expectancy effects
use automated procedures - rehearse, script; use single and double-blind procedures
manipulation check question
did you notice anything.....? If they don't mention your IV, your IV did not effect them
making observations and asking questions; includes descriptive research, correlational research, Case study, Archival Research, Content analysis
purpose is to evaluate the strength and direction of the covariation of two variables; relationships and associations
Concealed observation, nonparticipating
nonreactive, ethical problems if you are doing this in a place where people expect privacy
Ways to participate in natural observation
Concealed - join the group and not tell the group you've joined and are collecting data; Open - tell the group and get their permission, can get valuable information - the why behind the what, problem: bias - can lose objectivity
3 ways to collect data on behavior
ask for self-report, Make direct observations, Record physiological and neurological responses
two types of error
method - related to the instrument being used; trait - participant characteristics
increasing reliability - reduce error
many items or observations brings us closer to the true score, eliminate unclear items, standardize conditions, make instructions clear, clear evaluation criteria
Descriptive statistics -
Mathematical techniques for organizing, summarizing, and displaying a set of numerical data.
term is used to label the portion of statistics dealing with the
principles and techniques that allow researchers to generalize their findings beyond the actual data sets obtained- when based upon sample data but designed to extend beyond the sample, are called statistical inferences
Non-response bias -
a mid-stream mini-study done to see whether a non-response bias exists to get a feel for whether less-than-perfect response rates will restrict the desired level of generalizability.
, if each member of the population has at least some chance of being included in the sample, if the probability of any member of the population being drawn is known, the resulting sample is referred to as a probability sample. The four types of probability samples that we will consider are called simple random samples, stratified random samples, systematic samples, and cluster samples (allprobability samples
the educated guess as to the population's numerical characteristics is called a statistical inference
(I-alpha) The confidence interval is the probability of correctly
concluding that there is no-treatment effect
One-tailed test -
a hypothesis that specifies a direction; for example, when your hypothesis predicts that your program will increase the outcome.
a hypothesis that does not specify a direction. For example, if your hypothesis is that your program or intervention will have an effect on an outcome, but you are unwilling to specify whether that effect will be positive or negative,
you are using a two-tailed hypothesis.
A probability value considered rare in the sampling distribution, specified under the null hypothesis where one is willing to acknowledge the operation of chance factors.
Common significance levels are .01, .05, .10.
This method is used to insure that the overall experiment wise error rate does not exceed a=.05. Reduces the likelihood of a Type I error.
Example research question for t-test:
There will be no significant differences between Ele/Sec and HE students with respect to years of full time work experience
- Analysis of Variance is a Macro level Analysis of difference among or between 2 or more groups.
there is only one DV in factorial ANOVA, Factorial ANOVA has two independent variables which are crossed with each other and used as a
treatment on the DV.
Deals with the cell means, not the main effect means in a two-way ANOVA. Interaction exists to the extent that the difference between the levels of the first factor changes when we move from level to level of the second factor.
Main effect F
There are three values in the F column of a two-way ANOVA. Each of the three F's addresses a different null hypothesis. The first two Fs deal with the two sets of main effect menas. The third F deals with the interaction between the two factors with the focus of this F being on cell means
Means one of the two factors is between subjects, while the other factor is within subjects.
Any group with an above-average mean on the covariate has it's mean on the dependent variable adjusted downward, while any group with a below-average mean on the covariate has its mean on the dependent variable adjusted upward. These adjusted means constitute the best estimates of how the two groups would have performed on the dependent variable if they had possessed identical mean on the control (i.e. covariate)
variable(s) used in the study.
Indicates the degree to which variability in the dependent variable is explained by the set of independent variables included in the analysis. Adjust R2 is always smaller
than regular R2 , because the adjustment anticipates the amount of shrinkage that would be observed if the study were to be replicated with a larger sample
a multiplier term added to each predictor variable in a multiple regression equation after the predictor variables have been converted to standard score form.
The simplest kind of regression analysis. It has only 2 variables, one serves as the dependent variable and the other serves as the independent variable. The purpose of this kind of regression can be either prediction or
A statistical procedure for determining the magnitude of the
relationship between a single dependent variable and 2 or more independent variables. (Regression is used to either predict or explain.)
Y' = a + bX is the regression equation, b is the regression
coefficient. When the regression line has been positioned within the data points of a scatter diagram, b simply indicates the slope of the line.
Rise over run" How many predicted units of change (either up or down) in the dependent variable there are, for any one unit increase in the independent variable.
Multiple correlation coefficients used in multiple regression studies, R quantifies the extent to which the regression analysis achieves its objectives.
Coefficient of determination represents the proportion or percentage of the variability in the dependent variable that has been accounted for or explained by the study's independent variables. (Used in multiple regression analysis.)
A test of statistical significance when the research data are in the form of frequency counts for two or more categories.
Pearson chi square (X2 )
a nonparametric test of statistical significance that is used when the research data are in the form of frequency counts for two or more categories.
related to the measurement / data and it is the variable that we are measuring. The tendency is for this to be the demographic data.
A measure of central tendency corresponding to the most frequently occurring score in a distribution of scores.
Internal Validity Threats Quantitative
Testing, Instrumentation, statistical regression, differential selection, experimental treatment diffusion.
Internal Validity Threats Quantitative
Compensatory rivalry by the contol group, compensatory equallization of treatments, resentful demoralization of the control group.
External Validity of Research "Generalizability"
1) Explicit descrition of treatment 2) Multiple treatment interfernece, 3) Hawthron effect, 4) Novelty and disruption effects 4) Experimeter effect, 5) Pretest sensitization, 5) Measurment of dependent variable.
Method designed to increase the reliability of research by combining and analyzing the result of all types of the same product.
to obtain rich, descritpive data that is complex, subjective and details the particiapnts persepctive.
When would you use an interview?
Obtain percetions, feelings, attitudes, values. To obtain greater clarity. To build relationships.
What are some of the strengths of using an interview?
large amount of data quickly, wide range of info, large number of topics, immediate follow- up, allows for observation, allows for checking.
What are some of the limitations when using an interview?
Not familiar with jargon. Interviwers must be trained listeners and observers. Know hoe to construct converstation.
What are the three types of Depth Interviews
1) Unstructured-social conv-allows preliminary issues to surface 2) Semi Structured-Reseacher guides sequence, questions, probes. 3) Standardized structured-generally quantitative, tightly controlled, response options, no conversation
Waht are some of the limitations whe using Depth Interviews?
1) Bias becasue of interactions 2) Cooperation is essential 3) May not be truthful 4) Technique may compromise data
Qualitative Data Analysis
Long Table Approach-case study focus, group, interviews Content Analysis- Looking for patterns or themes. Coding can be used for both.
Types of Qualitative Research Design
1) Ethnographic- elicits cultural data 2) Phenomenological- real world, see thru eyes of others and can describe the essences of the experience. 3) Grounded theory-to find a basic problem or major concern.
Trustworthiness of Data
Credibility (triangulation), Dependability (stability of findings), Conformability(inquiry audit trail), Transferability (thick description), Authencticity( portray-mood, feelings)
When are case studies used?
1) The reasercher has little control over the events 2) The focus is on contemporary phenomenon within some real life context 3) "How" and "Why" questions are posted.
A case study is?
an empirical design inquiry that: investigates a contmeporary phenomenon within its real-life context especially when the boudries between the phenomenon and context are not clearly evident.
What are the four types of Case Study Designs
1) Single case-holistic 2) Single case embedded 3) Mutiple case-holistic 4) Multiple case-embedded
Type I error
Error of rejecting null hypothesis when in fact it is true (also called a "false positive"). You think you found a cause effect relationship but ONE IS NOT THERE
Type II error
error of failing to reject a null hypothesis when in fact it is false (also called a "false negative"). You think there is NO CAUSE EFFECT but THERE IS
Effects of being born and raised in a particular time or situation where all other members of your group has similar experiences makes your group unique from others
giving participants in a research study a complete explanation of the study after the study is completed needed for deception
in research, method by which participants are misinformed or misled about study's methods and purposes - must be told truth about this in debriefing
bell-shaped curve that results when values of a trait in a population are plotted against their frequency
Systematic review, RCT, cohort study,homogeneity, case control study, case report
Types of Evidence and Research
Systematic Review (including meta-analysis)
a review in which the primary studies are summarized, critically appraised, and statistically combined; quantitative w/specific inclusion/exclusion criteria.
RCT (Randomized Controlled Trial)
experimental study, random sampling, random assignment to experimental or control group to receive different tx or placebo.
prospective (forward in time) study; cohort w/similar condition is followed for defined period of time; comparison made to matched group w/out the condition.
Systematic review free of variations in the directions and degree of results b/w individual studies.
Case Control Study
Retrospective (backward in time) study; group with similar condition compared with group that does not have condition to determine factors that might have played a role in the condition.
Type of descriptive research in which only one individual is studied in depth, often retrospectively.
Systematic review of multiple RCT's (large N)substantial agreement of size and direction of tx.
Level 1a (A)
All or none case series. In absence of RCT, overwhelming evidence of substantial tx effect following intro of a new tx. (vaccine)
Level 1c (A)
average of all scores (X). Add all scores together and divide by the number of subjects (N). Used for interval and ratio data. Most common measure for central tendency.
Range, Standard Deviation, Normal distribution, Percentiles and quartiles
Measures of variability; determination of the spread of a groups scores
SD (Standard Deviation)
determination of variability of scores (difference) from the mean. Subtract each score from the mean, square each difference, add up all the squares, and divide by the number of scores. For interval, ratio data.
Symmetrical bell-shaped curve indicating the distribution of scores; the mean, median, and mode are similar. 1/2 the scores are above the mean and 1/2 below.
Most scores are near the mean, within 1 SD; approx 68% of scores fall within +1 or -1 SD of mean.
Frequency of scores decreases further from the mean (Normal distribution)
95% of scores fall +2 or -2 SD of mean.
99% of scores fall +3 or -3 SD of the mean.
allow determination of how likely results of study of a sample can be applied to whole population.
Standard error of measurement
estimate of expected errors in individual's score; a measure of response stability or reliability.
Tests of significance
estimation of true differences, not due to chance; a rejection of the null hypothesis. ie. Probability levels or alpha levels.
Alpha levels (preselected level of statistical significance)
0.05 or 0.01; indicates expected difference is due to chance ie. 0.05, only 5 X out of 100 or 5% chance. P value. Allows rejection of null hypothesis; there are true differences on the measured DV.
Degrees of Freedom
based on # of subjects and # of groups; allows determination of level of significance based on consulting appropriate tables for each statistical test.
based on population parameters; includes tests of significance based on interval and ratio data. Assume normal distribution in population, random sampling, variance in groups is equal.
parametric test compares 2 independent groups created by random assignment and identifies difference at a selected probability level ie 0.05.
T-test for paired samples
compares difference b/w 2 matched samples; 2 subtests are one-tailed and two-tailed t-test.
One tailed t test
based on a directional hypothesis; evals difference in data only on 1 end of distribution, either negative or positive.
based on a nondirectional hypothesis; evals differences in data on both positive and negative ends of a distribution; tests of significance are almost always two-tailed.
Analysis of Variance (ANOVA)
parametric test too compare 3+ independent tx groups or conditions at a selected probability level.
series of steps followed to solve problems including collecting data, formulating a hypothesis, testing the hypothesis, and stating conclusions
we overestimate our accuracy and our changes of success and ability to predict and explain
procedure that ensures every person in a population has an equal chance of being chosen to participate
when a specific word used in a question affects how respondents answer the question or the order of the questions
Simple (one way) ANOVA
compares multiple groups on a single independent variable ie. 3 sets of posttest scores