Construct Validity Research

Decent Essays
The above examples provide evidence that a personality measurement can be examined through its reliability. A good personality test should have the same findings in different occasions (i.e. test-retest reliability) and also all of the items in the test should be measuring the same thing (i.e. internal consistency). Nevertheless, personality measurement can be evaluated by its validity as well. Construct validity is one of the main subtypes of validity. Construct validity refers to the ability that a personality test measures what it is intended to measure. Discriminant validity is a subtype of construct validity, which refers to the extent that the concept that is not related to the test doesn’t emerge in the test. Soto, C. J., & John, O. P. (2009) tested the discriminant validity by comparing the BFI with the NEO PI-R. They showed that the correlation between the BFI and NEO PI-R facet scales has high discriminant validity. Each BFI facet scales correlated most with the corresponding NEO PI-R facet scales than with the other NEO PI-R facet. This research demonstrated that BFI is discriminant valid because it only correlates most with the corresponding items on the NEO PI-R. Furthermore, McCrae and Costa, P. T. (2004) found that NEO Five-Factory Inventory (NEO-FFI) had high…show more content…
In this meta-analysis, it included 4,378 MMPI and 1,793 the Rorschach articles. Then, the validity coefficients of the MMPI and the Rorschach Inkblot Test were compared. They found that the MMPI had the unweighted mean validity coefficients of .30 whereas the Rorschach had .29. The MMPI was more valid for studies using psychiatric diagnoses and self-report. In contrast, the Rorschach Inkblot Test was more valid for the objective. This meta-analysis showed that both the MMPI and the Rorschach Inkblot Test were valid in some
Get Access