Reliability Check
This type of reliability examines the consistency of test scores across time.
What is test-retest reliability?
This traditional type of validity concerns whether test items adequately represent the domain being assessed.
What is content validity?
Experts evaluate whether the items on a depression questionnaire adequately represent the relevant symptoms and behaviors.
What is evidence based on test content?
Students believe a personality test measures leadership because its questions appear relevant to leadership. This describes how valid a test looks to test takers, rather than whether it actually measures the construct.
What is face validity?
In a multitrait-multimethod matrix, it is the meaning of monotrait.
What is the same trait or construct?
This type of reliability examines how consistently items on the same test measure a construct.
What is internal consistency reliability?
This traditional type of validity examines how well test scores relate to an external criterion, such as job performance or GPA.
What is criterion-related validity?
Researchers ask students to explain their thought processes while answering questions to determine whether they interpret items as intended.
What is evidence based on response processes?
This term describes the theoretical network of relationships among a construct, observable behaviors, and other related constructs.
What is a nomological network?
Researchers correlate self-report and peer-rating measures of extraversion. Identify the MTMM correlation type.
What is monotrait-heteromethod?
Two instructors independently score the same student essays. This type of reliability examines the consistency of their ratings.
What is inter-rater reliability?
This traditional type of validity examines whether scores can be interpreted as representing the psychological attribute the test was designed to measure.
What is construct validity?
Researchers investigate whether items on a personality scale form the dimensions predicted by the test's theoretical framework.
What is evidence based on internal structure?
A company uses sales numbers to measure employee performance but ignores teamwork, customer service, and problem-solving. The criterion fails to capture important aspects of performance.
What is criterion deficiency?
A new anxiety scale correlates .81 with an established anxiety scale, providing this type of validity evidence.
What is convergent validity evidence?
This reliability formula is designed for tests with dichotomously scored items, such as correct/incorrect responses.
What is KR-20?
Researchers administer an employment aptitude test and correlate scores with employees' job performance six months later. Identify the traditional validity type and validation method.
What are criterion-related validity and the predictive method?
The source of validity evidence being of this statement: scores on a new procrastination measure correlate with an established procrastination measure and with students' GPA.
What is evidence based on relations to other variables?
A supervisor rates employees' job performance but allows personal friendships and favoritism to influence the ratings. This introduces irrelevant influences into the criterion measure.
What is criterion contamination?
This statistical technique uses two or more predictor variables to predict a single criterion variable, such as using SAT scores, high school GPA, and study habits to predict college GPA.
What is multiple regression?
This statistic measures agreement between two raters who classify observations into categories, while accounting for agreement that could occur by chance.
What is Cohen's kappa?
A job performance test excludes teamwork and communication, while its external performance ratings are influenced by supervisors' personal favoritism. These two problems threaten different aspects of the traditional validity framework.
What are content validity and criterion-related validity?
A university investigates whether using test scores to assign students to mandatory academic interventions produces unintended negative outcomes relevant to the proposed use.
What is evidence based on consequences of testing?
A university already uses high school GPA to predict college success. Adding an aptitude test increases the model's (R^2) from .30 to .42. This demonstrates this concept.
What is incremental validity?
A test predicts job performance with (r=.60). Approximately this is the percentage of the variance in job performance that is statistically accounted for by the test scores in a simple linear regression.
What is 36%?