Foundations of Testing
Measurement & Score Interpretation
Reliability
Validity Evidence
Criterion and Factor analysis
100

A test that suggests you have strong spatial reasoning, which may indicate potential success in engineering or architecture.

What is: an aptitude test

100

Height, Weight, Age, and Income are examples of this level of measurement 

What is: ratio

100

The formula X = T + E represents this theory

What is: classical test theory 

100

Experts rating whether items are essential provides this type of evidence

What is: content validity evidence

100

In Y′ = a + bX, b represents

What is: the slope

200

The three elements common to all psychological tests.

What is: Psychological construct, behavior, inference

200

If most students scored very high and only a few scored low, the distribution is this type of skew.

What is: negative skew

200

If two observers code aggressive behavior, this type of reliability is required.

What is: Inter-rater reliability 

200

Low correlation with an unrelated construct provides this type of evidence.

What is: discriminant validity evidence 

200

In a multiple regression, if two predictors correlate at r = .89, including both likely causes this issue.

What is: multicollinearity 

300

A decision where a student is dismissed if GPA falls below 2.0

What is: an institutional absolute decision 

300

Describe the strength and direction of this correlation coefficient: = .90

What is: very strong, positive relation

300

A student’s observed exam score fluctuates slightly each time they take the same test, even though their ability has not changed. This fluctuation represents this component of Classical Test Theory.

What is: Random measurement error 

300

Strong correlation between a new anxiety measure with another anxiety measure provides this type of evidence.

What is: Convergent validity evidence

300

Testing whether items load on three predicted factors uses this procedure.

What is: confirmatory factor analysis 

400

objective vs subjective: A test that uses structured true/false questions to assess someone's intrinsic motivation.

What is: an objective test

400

If r² = .25, what is the percentage of shared variance?

What is: 25%

400

A scale contains items measuring anxiety, depression, and stress. Cronbach’s alpha is calculated for the entire test. The estimate may be misleading because the test is this.

What is: Multidimensional 

400

If a job screening test predicts future job performance, this type of validity is demonstrated.

What is: predictive validity evidence 
400

A new statistics aptitude test is designed to predict success in a statistics course. However, final grades also include participation and attendance, which are unrelated to statistical ability. The criterion (success in the course) is now affected by this issue.

What is: criterion contamination

500

If you administer a depression test and combine it with clinical interview data and treatment history to reach a diagnostic conclusion, you are engaging in...

What is: an assessment 

500

A score that is -3 SD units below the mean represents this type of performance.

What is: extremely low, much worse then the rest of the sample

500

If a test–retest reliability coefficient is low, one possible explanation is that the construct being measured is not this.

What is: Stable over time 

500

A math placement test is administered during orientation. That same afternoon, students take an established standardized math exam. The strong correlation between the two demonstrates this type of evidence.

What is: concurrent validity 

500

In a pattern matrix, the item with the highest loading on a factor represents this.

What is: The strongest indicator of that latent factor 

M
e
n
u