Final Exam - Basic Concepts

Independent Variable

is the property that, when changed, potentially produces changes in other variables.

Dependent Variable

is the property whose value potentially changes as the result of changes in other variables

Reliability

the degree to which a measure produces the same result each time it is used in the same situations

What methods evaluate reliability?

Test-Retest, Alternate Forms, Internal Consistency, intrarater, interrater

What is test retest?

the same test or measure is given on two different testing occasions

What is Alternate Forms?

Two (ideally equivalent) versions of the test are given on two different testing occasions.

What is internal consistency method?

Evaluates the extent to which knowledge of how a person does on one item predicts how that person will perform on other items.

What are the different types of validity?

Construct, External, Statistical, Internal

Construct Validity

refers to the degree to which there is evidence that a characteristic or phenomenon of interest, and only that characteristic or phenomenon, is measured and/or manipulated by a test or procedure

What is validity?

the appropriateness of a conclusion or decision

External Validity

how well the results of a study generalize to, or represent, people or contexts besides those in the original study

Statistical Validity

is the extent to which a study’s numerical estimates are reasonable, precise, and replicable

Internal Validity

refers to a study’s ability to eliminate alternative explanations for the association

Content Validity

refers to the extent to which all facets (and only those facets) of a construct have been measured

Convergent Evidence of Validity

is demonstrated when a test measuring the construct of interest is shown to correlate with measures of other similar constructs

Discriminant Evidence Validity

is demonstrated when a test measuring the construct of interest is shown NOT to correlate

highly with measures of theoretically unrelated constructs

Criterion-related validity

is a source of validity evidence that is based on the ability of a test to predict or account for

performance on some other measure, called the criterion.

Concurrent Method (concurrent validity)

The test is used to account for variability in performance on an outcome (criterion)

that is measured at about the same time.

Predictive Method (predictive validity)

The test is used to forecast performance on an outcome (criterion) that is measured

later.

Face Validity

Whether or not a measure appears on the surface to measure a particular construct.

relationship between internal validity and external validity

The more you control the environment to increase internal validity, the more artificial the environment becomes, and the less likely it is that your findings will generalize to other situations

What are the three types of claims?

Frequency Claim, Association Claim, Causal Claim

Frequency Claim

A claim that describes a particular rate or degree of a single variable

Association Claim

A claim about two variables, in which the value (level) of one variable is said to vary systematically with value of another variable

Causal Claim

A claim arguing that a specific change in one variable responsible for influencing the value of another variable

Correctional Research Design

is one in which two or more variables are measured (NOT MANIPULATED) within a population of interest to describe the nature of the relationships between those variables

Non-experimental (correlational) designs

measures the statistical relationship between two or more naturally occurring variables without manipulating them or controlling extraneous factors

independent-groups design

some people will be assigned to a treatment or experimental condition, and different people will be assigned to a control condition

within-groups design

the dependent variable will be measured within each participant for all levels of the IV

one-group posttest-only design

All participants receive the treatment and then the DV is measured, There are no participants who are exposed to another level of the IV, and thus, no comparison group, and no way to tell if our treatment worked

one-group pretest-posttest design

An experiment in which a research recruits one group of participants; measures them on pretest; exposes them to a treatment, intervention, or change; and then measures them on a posttest

Interrupted time series design

Compares trends in the DM before treatment to trends after treatment

Control series design/non-equivalent control group interrupted time-series design

Compares trends in the DM before treatment to trends after treatment but with a addition of a nonequivalent control group

reversal design/withdrawal design

an extension of the A-B design that removes the treatment after it has been applied

alternating treatments design

different treatment strategies are alternated many times after the baseline is established

What is a factorial design?

A study in which there are two or more independent variables, or factors

What is a main effect?

the overall effect of one independent variable on the dependent variable, averaging over the level of the other independence variables

What is an interaction in a factorial design?

when the effect of one independent variable (factor) on the dependent variable depends on the level of another independent variable

Independent-groups factorial designs/ between-subjects factorial design

Both IVs are studied as independent groups, A 2 x 2 independent-groups factorial design has four groups/cells

Within-groups factorial designs

Both IVs are manipulated within-groups, A 2 x 2 within-groups factorial design also has

four cells/conditions, but every participant experiences every condition

Mixed Factorial Designs

One IV is manipulated as independent-groups and the other is manipulated within-groups, This design is intermediate between the within-groups design and the independent-groups design in terms of number of participants

What is the most important validity to evaluate for causal claims?

Internal Validity

What is the three criteria used to make a causal claim?

Covariance, Temporal Precedence, Internal Validity

What is Covariance?

The extent to which two variables are observed to go together, is established by the result of a study

What is temporal precedence?

The study’s method ensures that A comes first in time, before B

What is internal validity in establishing causation?

the study’s method ensures that there are no plausible alternative explanations for the change in B; A is only thing that changed