Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
29 Cards in this Set
- Front
- Back
What are the 4 criteria to evaluate the quality of selection measurements?
|
Reliability
Validity Utility Generalization |
|
The degree to which a measure is free from random error, or is more precise.
|
Reliability
|
|
A score on any measure must contain which two components?
|
True "score"
random error |
|
unusual circumstances
distractions poorly worded questions judgement calls and the mood of a reference giver are examples of |
random error
|
|
Reliability is calculated using
|
measurement repetitions
|
|
Inter-item reliability is
|
repitition in intems (same kinds of questions)
|
|
Test-retest reliability is
|
repetition in times (same test)
|
|
Inter-rater reliability is
|
repetition in raters (various interviewers)
|
|
Reliability is tested through
|
inter-item, test-retest, inter-rater
|
|
A perfect positive relationship for reliability is
|
+1
|
|
A perfect negative relationship for reliability is
|
-1
|
|
Strength of a reliability correlation is seen in
|
the compactness of x and y values on a scatter plot
|
|
The more compact a scatter plot is the
|
stronger the correlation
|
|
The less compact a scatter plot is the
|
weaker the correlation
|
|
what is a "good" level for reliability?
|
0.70
|
|
Refers to the extent to which the measure correlates with some criterion of interest
|
validity
|
|
Measures must be ____________ to be ____________.
|
Reliable, Valid
|
|
Statistically valid is the actual correlation between two measures is the "true correlation" multiplied by the _____________ of their reliabilities.
|
Square root
|
|
Intuitively valid is if a measure is mostly random error how can you expect it to correlate with ________ or ______.
|
Job performance, retnetion
|
|
A good level for validity measures is r=
|
.2 or .3
|
|
What are the methods for assessing validity?
|
criterion related
concurrent predictive content |
|
The reliability method does not rely on statistical derivation but is based on expert judgement
|
content validity
|
|
Validation method of establishing the validity of a personnel selection method by showing a substantial correlation between test scores and job performance scores.
|
criterion-related
|
|
Validation that gices measure to people already on the job, correlating with performance (or some other criterion) at that time.
|
concurrent validation
|
|
Validation that gives measure to job applicants, but is not used to hire. Then correlates it with performance several months later.
|
Prediction validation
|
|
Restriction in range is found with _________ validation, and is when most of your applicants already have high levels of what you're measuring.
|
Concurrent validation
|
|
Predictive validity is too
|
time consuming
|
|
In _________ the question of whether our validity of our measure generalizes to other jobs, organizations, kinds of people, and time period.
|
Generaliztion
|
|
When measuring _________ we ask, "how useful is the measure in terms of increasing overall profitability and allowing us to accurately select those who will succeed in the job, in a 'batting average' sense".
|
Utility
|