Deck 6: Evaluating Selection Techniques and Decisions.

Question 1

_______ is the extent to which a score from a test is stable and free from error.

A) Reliability
B) Validity
C) Psychometrics
D) Stratification

Answer 1

A

Question 2

When computing internal reliability, _____ is used for dichotomous items and _____ is used for interval and ratio items.

A) coefficient alpha / K-R 20
B) coefficient alpha / Spearman-Brown
C) K-R 20 / coefficient alpha
D) Spearman-Brown / coefficient alpha

Answer 2

C

Question 3

Test-retest reliability taps ____ stability.

A) form
B) temporal
C) item
D) score

Answer 3

B

Question 4

There are three major ways to determine whether a test is reliable. With the _______ method, several people each take the same test twice.

A) repeat reliability
B) test-retest reliability
C) dual reliability
D) alternate forms reliability

Question 5

In general, the longer the test, the higher its _______.

A) internal validity
B) external validity
C) internal reliability
D) external reliability

Question 6

To ask if all of the items measure the same thing, or do they measure different constructs, is related to ________.

A) internal validity
B) test-retest reliability
C) scorer reliability
D) item homogeneity

Question 7

The extent to which tests or test items sample what they are supposed to measure is related to the measure's _______ validity.

A) content
B) construct
C) criterion
D) concurrent

Question 8

_______ is an issue especially in projective or subjective tests in which there is no one correct answer.

A) Internal validity
B) Test-retest reliability
C) Scorer reliability
D) Item homogeneity

Question 9

An industrial/organizational psychologist correlates the responses to the even numbered items on a selection test with the responses to the odd-numbered items from the same test. Which of the following answers BEST describes the concern of the psychologist?

A) Parallel form reliability
B) Split-half reliability
C) Test-retest reliability
D) Scorer reliability

Question 10

With a __________ validity design, the test is administered to a group of employees who are already on the job.

A) concurrent
B) predictive
C) content
D) face

Question 11

The Spearman-Brown prophecy formula is used to adjust the correlation in which of the following reliability estimate methods?

A) Test-retest method
B) Alternate form method
C) Counterbalancing method
D) Split-half method

Question 12

_______ validity is a measure which refers to the extent to which a test score is related to some measure of job performance.

A) Content
B) Construct
C) Criterion
D) Concurrent

Question 13

When the two scores from alternate forms of a test are correlated and found to be similar, the test is said to have ________.

A) temporal stability
B) internal consistency
C) form stability
D) version consistency

Question 14

The process of counterbalancing test-taking order is used in which method of estimating reliability?

A) Test-retest reliability
B) Alternate-forms reliability
C) Internal reliability
D) All of the above use counterbalancing

Question 15

A student takes the Scholastic Aptitude Test (SAT) as a requirement to get into college. Her score on the test is 600. Three weeks later, she is asked to take the identical test again. This time she scores 500. This inconsistency in scores is an issue of:

A) internal reliability
B) parallel forms reliability
C) test-retest reliability
D) form stability

Question 16

With a _______ validity design, the test is administered to a group of job applicants who are going to be hired. The test scores, which are not used in the actual hiring decision, are then compared to a future measure of job performance.

A) concurrent
B) predictive
C) content
D) face

Question 17

The extent to which tests or test items sample the content that they are supposed to measure refers MOST specifically to:

A) face validity
B) content validity
C) construct validity
D) criterion validity

Question 18

The _______ of performance scores makes obtaining a significant validity coefficient more difficult with a concurrent validity design.

A) variety
B) restricted range
C) heterogeneous nature
D) cost

Question 19

In industry, _____ is used to establish the content validity of selection tests or test batteries.

A) job analysis
B) correlational analysis
C) job evaluation
D) an experiment

Question 20

If we use the weight of an infant to predict the subsequent performance of the infant in college, the weight measure is probably:

A) reliable and valid
B) reliable but not valid
C) not reliable but valid
D) not reliable and not valid

Question 21

If a small police department uses a cognitive ability test because a meta-analysis indicated cognitive ability is the best predictor of performance in the police academy, it is:

A) breaking the law
B) using the Taylor-Russell method
C) going to see a reduction in quality
D) using validity generalization

Question 22

Even though a test is both reliable and valid, it is not necessarily useful. The _______ were created to determine the probability that a particular applicant will be successful.

A) Taylor-Russell tables
B) Expectancy charts
C) Lawshe tables
D) Brogden-Cronbach-Gleser utility formula

Question 23

Construct validity is usually determined by correlating scores on a test with _______.

A) performance on the job
B) the items within the test
C) scores from similar tests
D) correlational analysis is not used

Question 24

The ______ are (is) used to determine the amount of money that an organization would save if it used a particular test in place of the test it currently uses to select employees.

A) Brogden-Cronbach-Gleser formula
B) Taylor-Russell Tables
C) expectancy charts
D) Lawshe tables

Question 25

_______ validity refers to the extent to which a test appears to be valid.

A) Content
B) Criterion
C) Construct
D) Face

Question 26

Barnum statements are most associated with:

A) known-group validity
B) face validity
C) concurrent validity
D) construct validity

Question 27

If test takers do not believe that items on a test measure what they are supposed to measure then the test probably lacks:

A) face validity
B) concurrent validity
C) criterion validity
D) reliability

Question 28

Which of the following sources contain reliability and validity information on various tests?

A) Radford Guide to Reliability
B) California Index
C) Validity Studies
D) Mental Measurements Yearbook

Question 29

Which of the following pieces of information is NOT required to use the Taylor-Russell tables?

A) Criterion validity coefficient
B) Selection ratio
C) Base rate
D) Reliability

Question 30

The extent to which a test found valid for a job in one location is valid for the same job in another location refers to the concept of _______.

A) the cross over effect
B) temporal stability
C) validity generalization
D) known group validity

Question 31

When the criterion validity coefficient is ____, and the selection ratio is ____, a test will have the most utility in selecting successful employees.

A) large / large
B) large / small
C) small / small
D) small / large

Question 32

______ is the basis for validity generalization.

A) Face validity
B) Known-group validity
C) Meta-analysis
D) Utility

Question 33

Even though a test is both reliable and valid, it is not necessarily useful. The _______ were/was developed to determine the amount of money that an organization would save if it used a particular test to select employees.

A) Taylor-Russell tables
B) Expectancy charts
C) Lawshe tables
D) Brogden-Cronbach-Gleser utility formula

Question 34

A test is considered to have _____ if there are race differences in test scores that are unrelated to the construct being measured.

A) differential validity
B) measurement bias
C) selection bias
D) adverse impact

Question 35

If the selection rate for any of the protected groups is less than 80% of the selection rate for either white applicants or males, the test is considered to have _______.

A) differential validity
B) adverse impact
C) selection bias
D) known group validity

Question 36

_______ is based on the assumption that tests that predict a particular component of one job should predict performance on the same component for another job.

A) Content validity
B) Validity generalization
C) Synthetic validity
D) Face validity

Question 37

If a police applicant is asked questions about her favorite hobbies and religious beliefs, she may feel the test is not valid. In this case, her impression demonstrates the importance of ______ validity.

A) construct
B) criterion
C) concurrent
D) face

Question 38

A researcher correlates scores on a test (Test 1) with scores on other tests (Test 2 and Test 3). The analysis demonstrates that the scores on Test 1 correlate highly with scores on Test 2 but do not correlate with scores on Test 3. This type of analysis is used to determine:

A) content validity
B) construct validity
C) concurrent validity
D) predictive validity

Question 39

Even though a test is both reliable and valid, it is not necessarily useful. The _______ are designed to estimate the percentage of future employees who will be successful on the job if an organization uses a particular test.

A) Taylor-Russell tables
B) Expectancy charts
C) Lawshe tables
D) Brogden-Cronbach-Gleser utility formula

Question 40

Setting your clock ten minutes fast will affect the _______ of the clock.

A) reliability
B) validity
C) psychometrics
D) speed

Question 41

What are the components of the Brogden-Cronbach-Gleser utility formula?

Question 42

What are the three main ways of determining test reliability and what type of stability does each method tap?

Question 43

What are the three types of criterion validity?

Question 44

San Antonio, Texas, has a system in which the names of the top three applicants for promotion are submitted to the Chief of Police who then selects one of the three to be the new Captain. This system uses:

A) the rule of three
B) top down selection
C) a passing score
D) banding

Question 45

With a _______ approach, the applicant is administered one test at a time.

A) multiple hurdle
B) top down selection
C) passing score
D) banding

Question 46

Single-group validity is very rare and is usually the result of _______.

A) small sample sizes
B) methodological problems
C) both a and b
D) none of the above

Question 47

A test predicts performance for two different groups of applicants (e.g., men and women); however, the test predicts the performance significantly better for men than it does for women. This exemplifies:

A) utility
B) single-group validity
C) differential validity
D) known-group validity

Question 48

What components are used in the Taylor-Russell Tables?

Question 49

In constructing a band, how many standard errors are normally used?

A) Three
B) One
C) None
D) Two

Question 50

If a test is valid for two groups, but more valid for one than the other it is said to have _______.

A) known group validity
B) differential validity
C) single group validity
D) validity generalization

Question 51

Single-group validity and differential validity are types of:

A) adverse impact
B) predictive bias
C) measurement bias
D) validation strategies

Question 52

What are three important aspects in determining the fairness of a test?

Question 53

If a test of reading ability predicts performance of white clerks but not African American clerks, the test has _______.

A) known-group validity
B) differential validity
C) single-group validity
D) validity generalization

Question 54

If an HR director believes the higher that applicants score on a test, the better they will do on the job, she could take a ________ approach to hiring decisions.

A) top-down
B) nonlinear
C) passing score
D) banding

Question 55

An HR director determines that all applicants who receive at least an 81 on their test will be able to perform the functions of the job. The hiring decision strategy to be used in this situation is:

A) multiple hurdle
B) top down selection
C) passing score
D) banding

Question 56

Which of the following hiring decision strategies takes into consideration the degree of error associated with any test score?

A) Multiple hurdle
B) Top down selection
C) Passing score
D) Banding

Question 57

What are the five methods for determining test validity?

Question 58

Which approach to employee selection would administer several tests to employees one at a time, with the least expensive tests being administered first; would score the various tests on a pass/fail basis; and would continue to test each applicant until he/she failed one of the tests?

A) Multiple-regression approach
B) Cutoff approach
C) Multiple-cutoff approach
D) Multiple-hurdle approach

Question 59

Of the available approaches to making a hiring decision, the _______ method results in the highest levels of adverse impact.

A) multiple hurdle
B) top-down selection
C) passing score
D) banding

Question 60

To compute a band, one needs the:

A) standard error
B) validity
C) F ratio
D) mean

Question 61

What are the three four approaches to making a hiring decision