CODESP Evaluating Selection Process Effectiveness 2 — Questions and Answers
Question 1: Which statistic best indicates whether a selection test predicts job performance across different subgroups equally well?
- Differential item functioning (DIF) (Correct answer)
- Cronbach's alpha
- Split-half reliability
- Standard error of measurement
Correct answer: Differential item functioning (DIF)
DIF analysis detects items that perform differently across subgroups (e.g., race, gender) beyond what ability differences would predict.
Question 2: A selection process yields a high false-negative rate. What is the primary organizational consequence?
- Qualified candidates are incorrectly rejected (Correct answer)
- Unqualified candidates are hired
- The test lacks content validity
- Pass rates are too high
Correct answer: Qualified candidates are incorrectly rejected
A high false-negative rate means the process rejects applicants who would actually have succeeded, causing loss of qualified talent.
Question 3: Under the Uniform Guidelines, when is a validity study required for a selection procedure?
- When the procedure has adverse impact and is used for employment decisions (Correct answer)
- Only when mandated by a court order
- Whenever more than 50 applicants are tested
- Only for physical ability tests
Correct answer: When the procedure has adverse impact and is used for employment decisions
The Uniform Guidelines require validity evidence when a selection procedure has adverse impact on a protected class and is used in employment decisions.
Question 4: What does a utility analysis estimate in the context of selection?
- The dollar value of improved performance gained by using a valid selection procedure (Correct answer)
- The pass rate of applicants on a test
- The proportion of variance explained by a predictor
- The reliability coefficient of a test
Correct answer: The dollar value of improved performance gained by using a valid selection procedure
Utility analysis quantifies the economic benefit of using a valid selection instrument compared to random hiring.
Question 5: Which method evaluates selection effectiveness by comparing the performance of hired applicants to a pre-employment test score, collected after hiring?
- Concurrent validation
- Predictive validation (Correct answer)
- Content validation
- Construct validation
Correct answer: Predictive validation
Predictive validation collects test scores at application and later correlates them with actual job performance data after hiring.
Question 6: The 'selection ratio' is defined as:
- The number hired divided by the number of applicants (Correct answer)
- The correlation between test scores and job performance
- The proportion of test items answered correctly
- The ratio of false positives to false negatives
Correct answer: The number hired divided by the number of applicants
The selection ratio equals the number of people hired divided by the total number of applicants for a position.
Question 7: Which index reflects the degree to which a test score is free from measurement error?
- Reliability coefficient (Correct answer)
- Validity coefficient
- Utility index
- Adverse impact ratio
Correct answer: Reliability coefficient
The reliability coefficient (e.g., Cronbach's alpha, test-retest r) indicates consistency and freedom from random measurement error.
CODESP Evaluating Selection Process Effectiveness 2
Which statistic best indicates whether a selection test predicts job performance across different subgroups equally well?