Old Reliable
This is the range of test scores within which we are confident that an individual’s true score lies.
What is a confidence interval?
The degree to which evidence and theory support the interpretations of test scores for proposed uses of a test. (American Education Research Association)
What is validity?
The degree to which test scores can be accurately interpreted as reflecting a particular concept
What is Construct Validity?
If an exam on learning and memory also contains questions about personality disorders (which weren’t covered in class) then it has issues with this.
What is content validity?
These are procedures that are designed to help us make inferences about populations.
What are inferential statistics?
This refers to the likelihood that on a second testing, an individual’s score is likely to be closer to the group mean than was his or her first score.
What is Regression to the Mean?
The factor of content validity associated with the psychological processes that participants actually use in a measure and the psychological processes that they should use.
What is Response Process?
The degree to which test scores are actually correlated with other measures that they should be correlated with.
What is Convergent Validity?
What an experimenter is concerned with if they’re worried that an item on their anxiety questionnaire actually measures depression.
What is structural validity (or internal structure)?
A sample of participants is assumed to represent this.
What is a population?
In applied test situations, this is usually reported along with the point estimates of a person’s scores.
What are confidence intervals?
This is the degree to which concepts that should not be related are, in fact, not related.
What is discriminant validity?
When test scores are actually related to an important criterion variable that they should be correlated with.
What is criterion validity?
This is a process of evaluating a test’s validity coefficients across a large set of studies.
What is validity generalization?
A value of this is generally considered to be a small effect size.
What is .10 or .20?
These are values that represent the results of a study as a matter of degree.
What are effect sizes?
This is a representation of the concepts, or constructs, of interest in a study, their observable manifestations, and the interrelationships among and between these.
What is The Nomological Network?
A researcher wants to develop a measure that predicts how well a person will do in the workforce. They should be concerned with what type of validity?
Criterion validity
This factor affecting observed associations says that variables measured by different methods are less strongly correlated than variables measured by the same method.
What is Method Variance?
Name one of the two factors that affect our confidence in concluding that there is a non-zero correlation in the population.
What is the size of the sample or What is the size of the correlation?
The amount of this is determined by reliability, worse reliability means having more of it.
What is attenuation?
These Multitrait-Multimethod Matrix correlations produce the strongest correlations between constructs.
What are monotrait monomethod correlations?
A researcher finds that his measure of tennis players’ skill matches up with their self-report ratings of their skill. The researcher has demonstrated this type of validity.
What is convergent validity?
These should match with the actual number of factors within a test.
What are the dimensions within the construct(s)?
In psychology, this person is often cited as providing rough guidelines for interpreting correlations as small, medium, or large associations.
Who is Jacob Cohen?