Upgrade to remove ads
Only $35.99/year

Research Methods - Chapter 4

Terms in this set (56)

Correlational Relationship
two or more dependent variables are measured to determine a relationship directions, magnitudes, and forms of the observed relationships
- if two covary, we are able to determine the direction (+ve or -ve) on a graph
Causal Relationships
one variable directly or indirectly influences another
Can causal relationships be bidirectional?
yes, each variable influences the other
ex. reducing amount of exercise leads to weight gain
ex. heavier people exercise less because of the increased effort involved
- therefore, exercise influences body weight and body weight influences exercise
Correlational Research
involves observing the values of two or more variables and determining what relationship exists between them, no attempt is made to manipulate variables
Why is it inappropriate to draw causal inferences from correlational data?
correlation is not causation
What are the characteristics of experimental research?
1. manipulation of one or more
independent variables
2. control over extraneous variables
Independent Variable*
a variable whose values are chosen and set by the experimenter, which is independent of the participant's behaviour (also called treatment, factor, or predictor variables)
Dependent Variable*
the variable whose value you observe and measure (also called outcome, results, or criterion variables)
Extraneous Variables
variables that may affect the behaviour you wish to investigate, but are not of interest for the present experiment
- if allowed to vary on their own, they can produce uncontrolled changes in the value of the dependent variable
What can be done to control extraneous variables?
- hold them constant
- randomize their effects across treatments
using random assignment
Demonstration
resembles an experiment but lacks an independent variable, simply showing what happens under a specific set of conditions
True Experiment
shows the effect of manipulating an independent variable
Internal Validity
the ability of a research design to adequately test the hypothesis: showing the changes in the value of your criterion variable are solely related to changes in the value of your predictor variable and not to changes in other variables
What factors threaten internal validity?
extraneous variables can provide alternative explanations for the findings of the study
Define Seven ways Confounding Variables Threaten Internal Validity
1. History
- specific events other than the treatment
occur between observations
2. Maturation
- performance changes due to age or
fatigue confounding the effect of the
treatment
3. Testing
- prior to treatment changes how subjects
respond in post-treatment testing
4. Instrumentation
- unobserved changes in observer criteria
or instrumental calibration
5. Statistical Regression
- subjects select treatment on basis of their
extreme scores: tend to move closer to
the mean on retesting
6. Biased Selection of Subjects
- groups of subjects exposed to different
treatments are not equivalent prior to
treatment
7. Experimental Mortality
- differential loss of subjects from the
groups of a study results in
nonequivalent groups
External Validity
the degree to which a study's results can be extended or generalized beyond the limited research settings and sample in which they were obtained
How do internal and external validity relate to each other?
- one type tends to decrease the other
- often the best you can do is reach a
compromise on the relative amounts of
validity on the research
- which one is more important depends on
the reasoning for conducting research
Simulation
attempting to recreate as closely as possible a real-world situation in the laboratory, used because the behaviour of interest could not be studied ethically in the real world
Realism
as realistic as possible, more relative to generalizing ex. Stanford Prison Experiment
Field Experiment
an experiment conducted in the participant's natural environment, can be easily generalized, but have little control over potential confounding variables
Third-Variable Problem
A problem that interferes with drawing causal inferences from correlational results
- a third unmeasured variable affects both measured variables causing the latter to appear correlated even though neither variable influences the other
Directionality Problem
a reason not to infer causality from correlational research, stating that the direction of causality is sometimes difficult to determine
Treatments
a level of an independent variable applied during an experiment; a specific combination of the levels of each factor
Experimental Group
a group of subjects in an experiment that receives a non-zero level of the independent variable
Control Group
a group of subjects in an experiment that does not receive the experimental treatment. The data from the control group are used as a baseline against which data from the experimental group are compared
Random Assignment
the process of assigning subjects to experimental treatments randomly
Confounding Variables
two variables that vary together in such a way that the effects of one cannot be separated from the effects of the other
Research Questions and Design
What: description and prediction
Why: explanation, understanding, and
control
Functions of Research Studies
1. exploratory data collection and analysis
2. hypothesis testing
Exploratory Data Collection and Analysis
- classifying behaviours related to a specific
area of research
- identifying relevant variables
- identifying relationships between
variables and/or between variables and
behaviours
Hypothesis Testing
- evaluating explanations for relationships between variables and or between variables and behaviours
- these relationships are either established in the literature or a researcher has sufficient evidence to make a claim that a relationship exists
Variable
- an element that varies and consists of at least two levels or values
- core unit of psychological research
- measured versus manipulated variables
Construct
abstract properties of things that cannot be measured directly by observation, must be operationalized
Operationalization*
the process of turning a concept of interest into a measured or manipulated variable
Spurious
when a relationship between two variables can be explained by a third variable
Ex. correlation between being outgoing and being satisfied with one's life. However, number of friends could account for relationship between being outgoing and satisfaction with one's life
Moderator Variable
a variable that is related to the independent and dependent variable and has an impact on the dependent variable
Define six types of variables:
1. Independent
2. Dependent
3. Confounding
4. Control
5. Extraneous
6. Moderator
What does the strength of the research depend on?
the level or degree of control exerted over all aspects of the study design
Randomization
the random effects are as likely to affect one group as the other
Comparison Group
a group of participants who receive a comparable treatment, provides a means of measuring the changes that occur specifically related to the treatment and not because of the special attention given to participants in an intervention study
Between-Subjects Design*
assign some of the participants to each of the various levels of the independent variables ex. assign some to treatment A and some to treatment B
Within-Subjects Design*
assign each participant to each level of independent variable
What does a between-subjects design require?
- a large number of subjects
- check that one level of independent
variable does not contaminate the other
- requires random assignment
- pretest is used to evaluate that random
assignment (make sure it does not result
in a systematic group difference)
- pretest-posttest control group design
Matched Pairs Design
- participants can be matched prior to random assignment of one member of the pair to a level of the independent variable
- provides extra degree of control than does random assignment to a between-subjects design
What does a within-subjects design require?
- each subject receives a level of the independent variable
- when subjects are tested repeatedly over time it is called 'repeated measures, within-subjects design'
Advantages of Within-Subjects Design
- each subject is his or her own control
- differences can be attributed to the
experimental condition or independent
variable
- fewer subjects are needed
- used in longitudinal studies
Disadvantages of Within-Subjects Design
- 'carryover effects' of one level of independent variable to another (practice effects, participant fatigue, associated with order of presentation)
- solutions: randomization of order of the
levels of independent variables,
counterbalancing
Experimental Error
a result of any influence on the dependent variable that is not solely due to the systematic change in the independent variable
Hypothesis
a specific statement of prediction which describes in concrete terms (not theoretical) what you expect will happen in your study
Alternative Hypothesis
describes the prediction (opposed to)
Null Hypothesis
describes all other possible outcomes with respect to the hypothesized relationship (trying to find support for: no difference)
One-Tailed Hypothesis
if your prediction specifies a direction and the prediction of the opposite direction
Type I Errors
An error of mistakenly rejecting the null hypothesis. The likelihood of making a Type I error is the criterion of significance.
Type II Errors
occur when the null hypothesis is accepted but is actually false, (should be fail-to-reject H0) the conclusion states that no relationship exists when one actually does
Validity
all extraneous factors need to be sufficiently controlled so that changes in the dependent variable are a result of changes in the independent variable
External Validity Expanded
- to whom do the results apply?
- extent to which the results can be
generalized to the population
Recommended textbook explanations

A Concise Introduction To Logic (Mindtap Course List)

13th EditionLori Watson, Patrick J. Hurley
1,960 explanations

Myers' Psychology for AP

2nd EditionDavid G Myers
900 explanations

Psychology: Principles in Practice

1st EditionSpencer A. Rathus
1,024 explanations

Myers' Psychology for the AP Course

3rd EditionDavid G Myers
955 explanations