Reading...
Play button
Play button
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;
19 Cards in this Set
- Front
- Back
|
Reliability
|
The degree of dependability, consistency, or stability of scores on a measure (either predictors or criteria) used in selection research.
|
|
|
Errors of Measurement
|
Factors that affect obtained scores but are not related to the characteristic, trait, or attribute being measured.
|
|
|
Obtained Score
|
X(obtained score = X(true) + X(error) - Obtained score for a person on a measure
|
|
|
True Score
|
X(obtained score = X(true) + X(error) - True score on a measure
|
|
|
Error Score
|
X(obtained score = X(true) + X(error) - error score on the measure
|
|
|
Reliability Coefficient
|
An index that summarizes the estimated relationship between two sets of measures.
|
|
|
Test-retest
|
The same measure is used to collect data from the same respondents at two different points in time.
-FACTORS THAT AFFECT RELIABILITY - Day-to-day changes in test-takers - Changes in site of test administration - Memory (overestimates reliability) - Learning (underestimates reliability) |
|
|
Parallel or Equivalent Forms
|
Administering two equivalent versions of a measure to the same respondent group.
|
|
|
Internal Consistency
|
The various parts of a total measure should be so interrelated that they can be interpreted as measuring the same thing.
|
|
|
Interrater Reliability Estimates
|
Shows the extent to which all parts of a measure are similar in what they measure; involves single administration of one measure.
|
|
|
Split-half Reliability
|
Single administration or subdivided test reliability measures. The measure is divided or split in to two halves so that scores for each part can be obtained for each test taker.
|
|
|
Kuder-Richardson reliability
|
Takes average of the reliability coeff. that would result from all possible ways of subdividing a measure, to solve the problem of how best to divide a measure. Good for Yes/No questions. Or questions with two answers.
|
|
|
Cronbach's coefficient alpha
|
Correlates every possibility. Better for likert or multiple choice. Sensitive to # of items on scale. More is better, but don't cause fatique. 7 point scale is best(enough discrimination)
|
|
|
Measurement Error
|
Those factors that affect obtained scores but are not related to the characteristic, trait, or attribute being measured.
|
|
|
Interrater agreement
|
Used with categorical data; two raters
|
|
|
Interclass agreement
|
Used with interval data; two raters
|
|
|
Intraclass agreement
|
Used with interval data; three or more raters
|
|
|
Reliability coefficient
|
The extent (in % terms) to which indiv. dif. in scores on a measure are due to "true" dif. in the attribute measured and the extent to which they are due to chance errors. Higher is better. Depends on time(test-retest)(lower), # of items(higher), sample size (higher).
|
|
|
Standard Error of Measurement
|
The estimated error in a particular individual's score on the measure.
|
