Chapter 5: Identifying Good Measurement

Convergent validity

Your measure is strongly associated w measures of similar construct

Discriminant validity

Your measure is NOT associated w measures of dissimilar construct

Criterion validity

Your measure is correlated with relevant outcomes. Does it correlate with key behaviors?

Face validity

It looks like what you want to measure, at face value

Content validity

The measure contains all the parts that your theory says it should contain

Known-groups paradigm

Asking someone in the field to evaluate your study

Test-retest reliability

Ppl get consistent scores on a test every time the measure is used

Inter-rater reliability

Consistent scores no matter who does the measuring (across different people)

Internal reliability

Pertaining to a measure; ppl give consistent scores on every item of a questionnaire

Validity

Accuracy; the operationalization is measuring what it is supposed to measure (applies to measures and studies)

Reliability

Consistency; the results of the measure are consistent (applies to measures and studies)

Internal reliability

The extent to which multiple measures, or items, are all answered the same by the same set of people; different from internal validity

Cronbach’s alpha

An average of all of the possible item-total correlations