Study reliability and validity
The validity of a study is the degree to which it accurately measures its claims. To assess validity researchers use a range of different methods. They fall into four main categories: face valid, content valid, criterion value, and construct validation.
- Face Validity: This is the easiest form of validity. In essence, it measures the degree to which an experiment appears to be measuring what it claims. The subjective evaluation of whether the measure makes sense is what determines face validity.
- Content Validity refers the extent of coverage by a measure for the construct to be measured. The content validity of a measure is determined by an expert’s judgment. For example, a panel reviewing the items in a questionnaire will determine whether the items accurately reflect the construct to be measured.
- The term “criterion validity” refers to how closely a measurement is tied to an external criteria, like a gold-standard or measure for a similar construct. It is common to assess the validity of the criterion by comparing scores from the test measure with scores obtained on a standard measure for the construct being measured or another construct.
- Construct Validity – Construct validity is the degree to which the measure being tested accurately measures the underlying concept that’s been studied. The construct validity of a measure is usually assessed by looking at the relationship between that measurement and another one which theoretically relates to the construct under study.