How Do Psychologists Determine Whether a Measurement Scale Is Good? A Quarter-Century of Scale Validation with Hu & Bentler (1999).

Many psychologists rely on surveys, questionnaires, and measurement scales because psychological constructs like depression, motivation, or extraversion cannot be directly measured with physical instruments. Scale validation crucially provides evidence that scores from such scales capture their intended target. The prevailing scale validation approach involves comparing factor-analytic model fit indices to suggested benchmarks, and it is so engrained in psychological research that the article proposing the benchmarks is among the most cited works across any scientific discipline. However, methodological research finds that psychologists overgeneralize the benchmarks so that they no longer function as originally intended. This has widespread implications for psychologists and casts some doubt on conclusions regarding the validity of our measurement scales. This review covers the history and origin of scale validation benchmarks, how benchmarks rose to prominence and became overgeneralized, recently proposed alternatives to traditional benchmarks, and future directions in this methodological area that affects many subfields of psychology.