1. The ratio level of measurement would include which of the following?
a. political affiliation
b. amount of books owned
c. order of finishing test
d. GRE score
2. Which level of measurement conveys the most information?
a. nominal
b. ordinal
c. interval
d. ratio
3. Which of the following is NOT an example of reliability?
a. consistency
b. performing the same in the future as in the past
c. the test doing what it is supposed to do
d. measuring the same thing more than once with the same outcome
4. A score that you would actually record is a(n) ______________ score.
a. observed
b. true
c. error
d. false
5. What are the two components of error scores?
a. method error and consistent error
b. standard error and method error
c. trait error and standard error
d. trait error and method error
Unit 2 Examination
97
GRM 697 The Research Process
6. A measure of how stable a test is over time is an example of which of the following?
a. inter-rater reliability
b. test-retest reliability
c. parallel forms reliability
d. internal consistency
7. _____________ describes a measure used to compare two different tests with the same group of participants to see how closely correlated the two sets of scores are with each other.
a. Inter-rater reliability
b. Test-retest reliability
c. Parallel-forms reliability
d. Internal consistency
8. What is the name of the individual credited with devising levels of measurement in which different measurement outcomes can be classified?
a. Binet
b. Stevens
c. Cattell
d. Wechsler
9. What is one way to obtain a criterion validity estimate?
a. ask an expert for his or her opinion
b. assess the underlying construct on which the test is based and correlate these
scores with the test scores
c. select a criterion and correlate scores on the test with scores on the criterion
d. obtain a Pearson Product Moment correlation coefficient for two different forms of the test given at different times
10. Intelligence tests usually compare the performance of a child against other children of the
same age. This type of test is called a(n) ______________ test.
a. achievement
b. standardized
c. norm-referenced
d. criterion-referenced
11. Tests such as the Denver Developmental Screening Test are used _______________.
a. as dependent variables
b. for entrance to a program to identify strengths and weaknesses
c. to distinguish among people for selection purposes
d. to determine if program goals were met
Unit 2 Examination
98
GRM 697 The Research Process
12. What type of test defines a specific level of performance (or mastery) of some content
domain?
a. standardized test
b. researcher-made test
c. norm-referenced test
d. criterion-referenced test
13. The Graduate Record Examination and the Miller’s Analogy Test are generally used for
_______________.
a. placement
b. selection
c. evaluation of a program
d. diagnosis
14. What is the computed number for the proportion of test takers who get an item correct?
a. item analysis
b. discrimination index
c. difficulty index
d. attitude index
15. What is the computed number for how well an item distinguishes between the “knowing” and the “unknowing”?
a. item analysis
b. discrimination index
c. difficulty index
d. attitude index
16. Which one of the following is a disadvantage of multiple choice tests?
a. can be used to assess almost anyone
b. limits the kind of content assessed
c. are relatively easy to score
d. poor writers are not penalized
17. Which level of measurement is very similar to Thurstone-like scales?
a. ordinal
b. nominal
c. interval
d. ratio
Unit 2 Examination
99
GRM 697 The Research Process
18. What is the range of 5, 8, 10, 14, and 11?
a. 48
b. 9.6
c. 10
d. 9
19. What is the average amount that each score varies from the mean of the set of scores?
a. the range
b. the standard deviation
c. the mean
d. the normal curve
20. How can descriptive statistics be defined?
a. describing elements of a distribution
b. relating the data to a larger population
c. developing a research question
d. identical to inferential statistics
21. Which measure of variability is the most direct way to measure how dispersed a set of scores
is?
a. the mean
b. standard deviation
c. range
d. variance
22. When computing the standard deviation, what does it mean when the sum of the deviation about the mean is NOT 0?
a. The data set has a great amount of variability.
b. The data set has at least one extreme score.
c. The data is too small.
d. The mean of the data set was computed incorrectly.
23. Which measure of variability describes the average deviation of each score from the mean?
a. range
b. standard deviation
c. mode
d. mean
Unit 2 Examination
100
GRM 697 The Research Process
24. What measure would be used to compute the average gender of subjects?
a. mean
b. mode
c. median
d. standard deviation
25. Which measure would be used to describe the average class ranking of algebra students?
a. mean
b. mode
c. median
d. standard deviation