Which of the following is an item-writing guideline for the construction of multiple- choice items?
A. Generally, especially with young children, the stem should consist of an incomplete statement rather than direct question.
B. Don't ever use all-of-the-above alternatives, but use a none-of-the-above alternative to increase an item's difficulty.
C. Typically, make the later answer options, such as C and D, the correct answers.
D. Supply clues to the correct answer by using alternatives of dissimilar lengths.
Ques. 2The higher the decimal amount for p, the more difficult the item.
a. True
b. False
c. Not enough information
Ques. 3What approximate Item Difficulty Index average is closest to the optimal item difficulty level for maximizing variability and reliability?
a. .24
b. .09
c. .99
d. .49
Ques. 4During recent years, when results of NAEP tests are contrasted with results of state accountability tests, which of the following statements best captures the relationship between those two sets of results?
A. Students' performances on NAEP and on state accountability tests are essentially equivalent.
B. Students' performances on a state's tests are classified higher than those same students' scores on NAEP.
C. Students' performances on NAEP are typically better than those same students' scores on their state's accountability tests.
D. Students in a state usually score better on NAEP than they do on their own state's mathematics tests, but less well on their state's reading tests than they do on NAEP reading tests.
Ques. 5Which of the following sources of validity evidence are teachers most likely to collect?
A. Test content
B. Response processes
C. Internal structure
D. Relations to other variables
Ques. 6Two groups are given the Wechsler Intelligence Scale for Children-Fourth Edition. Group one is at a level of borderline impaired or delayed (mental retardation), and group two is at a level of superior intelligence? What type of validity study is this?
a. Contrasted group study
b. Concurrent study
c. Predictive study
d. Split-half study
Ques. 7If a teacher knows that a student scored below 100 (below average) on an intelligence test, the teacher might assume the student is not going to perform well and have lower expectations of the student? Which of the following is a descriptive for this situation?
a. Criterion contamination
b. Content contamination
c. Criterion-related validity
d. Criterion validity
Ques. 8When students' test scores areas predictedcorrelated positively with those students' scores on a test aimed at a similar measurement mission, of what is this an example?
A. Construct-irrelevant variance
B. Divergent validity evidence
C. Convergent validity evidence
D. Construct underrepresentation
Ques. 9A regression line is used in validity studies to
a. predict criterion performance based on predictor test scores.
b. evaluate the usefulness of test scores for prediction purposes.
c. predict the number of test-takers who will exceed the prediction.
d. All of the above
Ques. 10In evaluating the validity evidence for use of a test for determining giftedness and eligibility for a gifted/talented program, school district personnel emphasize the high reliability that has been demonstrated for the test. Which statement below reflects the concern of the AERA/APA/NCME Standards for this emphasis?
a. Integrating of numerous lines of evidence
b. Using internal structure evidence
c. Ignoring validity coefficients
d. Requiring high reliability coefficients