Upgrade to remove ads
Only $2.99/month

T&M exam 2

Terms in this set (49)

Face Validity
How valid a test looks to those involved
Content Validity
How adequately a test samples behavior it is designed to sample
Criterion-Related Validity
How adequately a score can be used to infer an individual's standing on some criterion
Construct Validity
Appropriateness of inferences drawn from test scores regarding standing on a construct
Validty Coefficient
Correlation between test score on criterion measure
Concurrent
Test scores and criterion measure at the same time
Predictive
Test scores, then criterion measure taken in the future
Incremental Validity
Do additional predictors explain something else about criterion
Standard Error of Estimate (SEE)
Margin of error expected in the predicted criterion score
Construct
Informed, scientific idea hypothesized to describe or explain behavior
Convergent Validity
A test correlates highly with other tests of the same construct
Discriminant Validity
A test does not correlate with other tests of different constructs
Content
The actual items that make up the test
Criterion
Standard against which a test or score is evaluated
Validity
Extent to which a test measures what it purports to measure in a specific context
Reliability
Repeatability or consistency of measurement
Reliability Coefficient
Indicates ratio between true score variance and total variance on a test
Test-Retest
correlating pairs of scores from the same people on two different administrations of the same test
Internal Consistency
use of a single test administered on one occasion to estimate reliability
Split-half Reliability
Correlating scores obtained from equivalent halves
Spearman Brown Formula
Allows estimates of internal consistency from a correlation of two test halves
Kuder Richardson Formula
similar concept as Spearman-Brown - used with items are dichotomous
Cronbach's Coefficient Alpha
The mean of all possible split half correlations - used with continuous variable items
Inter-Scorer Reliability
Degree of agreement or consistency between two or more scores
Standard Error of Measurement (SEM)
Used to estimate the extent to which an observed score deviates from a true score
Confidence Intervals (SEM)
Range of test scores likely to contain the true score
Test Conceptualization
Coming up with an idea for a test
Content-related Questions
What is the test designed to measure? What are the objectives? Is there a need?
Person-related Questions
Who will use the test? Who will take the test? Is special training required? Who will benefit?
Test-related Questions
What format should be used? More than one form? Types of responses? How will meaning be attributed to scores?
Norm-referenced
Distinguish between high and low scores - relative standing
Criterion-referenced
Distinguish between mastery and nonmastery - pass/fail
Scaling
Setting rules for assigning numbers in measurement
Rating Scales
Groups of words/symbols to indicate strength of trait, attitude, emotion
Summative Scale
Test score obtained by summing ratings across all items
Likert Scale
alternate responses on agree/disagree or approve/disapprove type of continuum
Paired Compaisons
Compare forced-choice, dichotomous items
Comparative Scaling
Sorting and rank ordering items in comparison with all others
Categorical Scaling
sorting items into alternative categories
Guttman Scaling
Items range sequentially from stronger to weaker expressions of the construct being measured
Item Pool
Reservoir from which items will be drawn or discarded for final version of test
Selected Response
Choose response from set of alternatives
Constructed Response
Supply or create correct answer
Item Difficulty Index
represents the proportion of testtakers who got the item right (0-1)
Item Discrimination Index
Indicates how well an item separates between high and low scores (-1 to +1)
Item Reliability Index
Relationship between item SD and item to test score correlation
Item Validity Index
Relationship between item SD and correlation with criterion measure
Cross Validation
Revalidation of a test on a sample other than those on whom test performance was originally found to be a valid predictor of some criterion
Validity Shrinkage
Expected decrease in item validities observed during cross validation
YOU MIGHT ALSO LIKE...