Upgrade to remove ads
Introduction to educational research
Terms in this set (75)
Pure science that aims to increase the scientific knowledge base.
Scientific study that aims to solve practical problems
Studies that have not been considered because they do not give significant results/ the results they wants.
A formal, objective, systematic research process to describe, test relationships, or examine cause-and-effect interactions among variables
Used to learn about trends in a large population - a "sample." Purpose to DESCRIBE opinions, beliefs, attitudes, etc. Results reported ONE VARIABLE at a time (no correlations computed). SELF-REPORT: + cheap, quick; --impression formation effect & frame-of-reference effect. They are comprised of ITEMS.
Studies that measure two or more variables and their relationship to one another; not designed to show causation.
This is the process of organising an experiment so that the effects of the IV upon the DV can be investigated. There are 3 basic types, independent measures design, repeated measures design and matched pairs design.
An experimental method without random sampling, confounding variable not controlled, provides only tentative cause-effect.
An emphasis on words and feelings; research problems/methods evolve as understanding of topic increases; smaller sample sizes; relies on categorizing & organizing data into themes or patterns to describe & synthesize the data; high level interaction with subjects; many possible contexts & meanings for different people; subjective by nature.
Participant tells a story that describes their unique experiences.
Detailed descriptive studies of human societies. In cultural anthropology, an ethnography is traditionally the study of a non-Western society.
grounded theory design
systematic, qualitative procedure used to generate a theory that explains, at a broad conceptual level, a process, an action, or an interaction about a group of people with similar experiences.
A factor in the experiment that can be changed. Must have at least 2 .
Attribute - specific instances that vary within the variable. Male and female are attributes of Gender.
Variable varies in KIND - can be placed into distinct categories, according to some characteristic or attribute. (i.e. gender- male/female)(i.e. religion- catholic, Muslim, Hindu, Mormon).
Variable varies in amount - characteristic that can be measured numerically
(IV) The experimental factor that is manipulated; the variable whose effect is being studied
(DV) The outcome factor; the variable that may change in response to manipulations of the independent variable.
The group of people that a researcher wishes to learn something about.
Collecting data from a smaller group (subgroup) of participants that are representative of the population being researched. +statistically unnecessary. -too expensive to collect from total pop.
A subject about which one wishes to find information
Area of concern that one wants to address
research purpose statement
Statement of intent that outlines what is going to be studied, how and who and the context/ variable, population, location.
The question the study is to answer. Typically begins with "does," "do," or "is." Phrasing of questions provides hints about study design: SURVEY - describe, illustrate; COORELATIONAL - related to, predict, associated; EXPERIMENT - causes, leads to, affects.
A way of ensuring that a sample of people is representative of a population by giving everyone in the population an equal chance of being selected for the sample
Assigning participants to experimental and control conditions by chance, thus minimizing preexisting differences between those assigned to the different groups. RELATES ONLY TO EXPERIMENTS!
Invented entities that are inferred to exist based on observations of behavior. Theoretical entities, or concepts, that enable one to discuss something that CANNOT be seen, touched, or measured directly.
operationalization of constructs
How the researcher actually measures/manipulates their variables. Never perfect - a measure never perfectly overlaps witht he construct it intends to measure.
The degree to which a study appropriately answers the question being asked
QUALITY of OPERATIONALIZATION. Variable is measured in a fair, convincing, & logical manner. Experimental demonstration that a test is measuring the construct it claims to be measuring (NOT: Example of test measuring moral reasoning, but actually measures reading ability). 3 parts: measure contamination, measure deficiency, measure relevance.
Extent to which we can generalize findings to real-world settings to other contexts: POPULATIONS, ENVIRONMENTAL(geographical regions), TEMPORAL(times - past or future).
The extent to which an experiment shows convincingly that changes in behavior are a function of the independent variable and NOT the result of uncontrolled or unknown variables. Relates only to experiments.
Used in quantitative data collection, TEST. Measures either a person's APTITUDE or ACHIEVEMENT
A person's POTENTIAL for learning a certain skill
Current COMPETENCE - knowledge and skills gained from experience and education
Usually questionnaires or interviews that measure how people report that they act, think, or feel.
The process by which a person uses behavior and appearance of others to form attitudes about them. Not answering a survey honestly in order to impress the researcher.
The degree to which people's perceptions of themselves is skewed by their comparison group.
Measures of bodily responses, such as blood pressure or heart rate, used to determine changes in psychological state. Ex. brain activity (MRI, PET, EEG, EMG). +shows link betw. psychology and physiology. -time, expense, difficult to measure enduring phenomena.
Direct observations of behaviors by trained raters. + Deals with actual behaviors, not perceptions/intuitions. -Slow data collection; expensive; some behaviors rare or difficult to observe.
tendency of participants to react to an observer's presence by behaving in unusual ways
Influence on the data reported by an observer that results from the observer's AWARENESS that others are evaluating the data he reports.
A sample that consists of the ENTIRE population
A small group whose characteristics accurately reflect those of the larger population from which it is drawn. This type of sample is often used as the beginning of a study or theory.
A sample that fairly represents a population because each member has an equal chance of inclusion. Ex. name from hat.
A survey of selected groups within a population. This sample technique can save time and expense, but may not give reliable results unless the groups are representative of the population. Caution: groups must be representative of the broader population of interest.
The same as cluster sampling except that there are levels to how the groupings are organized - randomly sample within those groups. Caution: groups must be representative of the broader population of interest. Used for LARGE DATA COLLECTION.
stratified random sampling
Choose a sample that EMPIRICALLY MATCHES the population on certain characteristics. Powerful approach to ensure you sample is representative on key demographics.
The process of taking a bigger sample if the group you wish to study makes up a small percentage of the whole population. To ensure statistical validity in rare subgroups. Must statistically weight this group as being the same percentage as the sample.
Convenience sampling - A subgroup that differs an important ways from the larger group (or population) to which it belongs. Picking participants that are easy to acquire. --Self-selection bais: baised sample that does not reflect population as a whole.
People who volunteer to participate differ from those who do not. The differences between population parameters and sample statistics which may occur because some respondents refuse to be interviewed.
Participants help recruit other participants. Very powerful for hard-to-find samples. Works best if participants rewarded for bringing in other participants.
The ability of a test to yield very similar scores for the same individual over repeated testings. CONSISTANCY in MEASUREMENT across time, observers, or instruments. ALL measurement includes some error. Measured Score = True Score + Error. Important: Quantify how much error exists.
4 types: test-retest, interrater, internal consistency, alternate-forms. High reliability does NOT equal high construct valiability. RELIABILITY provides a CEILING to CONSTRUCT VALIDITY. Your measure can only be as valid as it is reliable.
A method for determining the reliability of a test by comparing a test taker's scores on the same test taken on separate occasions. Ex. IQ score.
Consistency of results when more than one person measures performance. Used in real-world situations, rater is well-trained, rating criteria are written down & clear, familiarity with criteria, observations made independently, rater is blind to research question.
internal consistancy (reliability)
Extent to which all items within an assessment reliably measure the same construct. Measured via Cronbach's Alpha: average correlation between all items.
An indicator of INTERNAL CONSISTENCY reliability assessed by examining the average correlation of each item (question) in a measure with every other question. Used as an assessment of reliability, should be greater than 0.90.
The correlation between two forms of a test with different items that are measuring the same attribute.
A measure of the relationship between two continuous variables.
A 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. The amount of scatter suggests the strength of the correlation (little scatter indicates high correlation).
Cohen's kappa coefficient
Used to report INTERRATER RELIABILITY. It adjusts for agreement solely due to chance. By convention, we seek reliability of > .70
The measure includes superfluous/unnecessary questions.
The measure fails to include necessary questions. Portion of a construct that is not represented by the actual measure.
The measure accurately overlaps between measure and construct. VALIDITY communicated/expressed in 6 ways/subtypes: FACE , CONTENT , CONVERGENT, DISCRIMINANT, CONCURRENT, PREDICTIVE VALIDITY.
It looks as if it measures what it is supposed to measure. Assessed via subjective judgement (not quantified).
Degree to which an instrument measures the entire construct. It is not deficient or contaminated. Assessed through experts' opinion (not quantified).
Extent to which scores obtained from one procedure are positively correlated with scores obtained from another procedure that is already accepted. By convention, we desire correlations > .70
Beck Depression Inventory (BDI)
Assesses the severity of depressive symptoms and can be used to track course of symptoms.
The lack of a relationship among measures which theoretically should not be related. By convention, we desire correlations < .30
Extent of correlation between selection and performance scores, when measured AT THE SAME TIME.
The process of validation an instrument by showing that it can distinguish between groups. Test the measure by using two comparison groups whose behavior can easily be predicted. Ex. Minnesota Multiphasic Personality Inventory (MMPI).
Validation strictly based on empirical resutls. Completely atheoretical approach. Instrument items have LOW FACE validity. + instrument is difficult to fake/deceive.
Degree that scores on 1 tests correlate to scores on another (taken at different times IN THE FUTURE). Challenge to high perdictive validity: longer the lag time, the more opportunity for external factors to affect relationship between predictor and criterion. B.y convention, predictive validities of .4 - .5 are impressive
The correlations between different measures of the same trait obtained at the same time. Rarely reported.
People who respond to a survey, either in interviews or by self-administered questionnaires. They COMPLETE surveys. Surveys comprised of ITEMS.
Relates to our mind's ability and tendency to organize and comprehend all visual input into a special relationship - the BOUNDARY of a construct.
THIS SET IS OFTEN IN FOLDERS WITH...
YOU MIGHT ALSO LIKE...
Research Methods Final
Chapters 5, 6, 7, and 8
Soci Exam 2
OTHER SETS BY THIS CREATOR
Middle School Praxis 0049
Common Assessment Review