Item response theory involves which of the following procedures?
a. Standardization
b. Identifying relevant conditions that affect scores on a test
c. Determination of cut scores for each item
d. Examining individual items for quality
2. Which of the following measures of reliability does NOT require that test takers take a test twice?
a. Test-retest
b. Alternate forms
c. Parallel forms
d. Split-half
3. Splitting the test and correlating scores on one half to scores on the other half will reveal
a. Homogeneity of items.
b. Internal consistency.
c. Whether the items are measuring the same construct.
d. All of these
4. Justina, an undergraduate in Testing and Assessment, creates a new scale of self-perceived athleticism. She is concerned that some of her items might measure self-confidence instead of the trait she wants to capture. Justina should compute
a. Test-retest reliability.
b. Internal consistency.
c. Intra-rater reliability.
d. True scores.
5. If you add items to a test that are unrelated to items already on the test, which type of reliability is most likely to be affected?
a. Internal consistency
b. Parallel forms
c. Inter-rater
d. Alternate forms
6. If you want to compute the possible range of scores for an individual on an intelligence test, you should
a. Use multiple scorers.
b. Compute the standard error of the estimate.
c. Compute the person's "true score."
d. Have the person take the test many times.
7. Which of the following is TRUE about error in psychological measurement?
a. Error means the test has poor psychometric soundness.
b. Error is unrelated to variability.
c. Some error is expected.
d. Error only happens when validity is poor.