construct validity
The extent to which a measure actually captures the unobservable concept it claims to measure.
As defined in Michele Gelfand on Rule Makers, Rule Breakers
Where it comes up · 2
- Jim Manzi on the Oregon Medicaid Study, Experimental Evidence, and Causality1 claim
- Michele Gelfand on Rule Makers, Rule Breakers1 claim
Most important claims · 2 of 2Search all claims for “construct validity” →
- Because tightness-looseness is not directly observable, validating it requires multiple measures—surveys of the permissible range of behavior across situations and countries, coding ethnographies of preindustrial societies, dictionaries, brain imaging, and computational models—seeing whether predictions are borne out homologously across levels.Michele Gelfand on Rule Makers, Rule Breakers
- The statistically significant reduction in depression apparently occurred within the first month of the study, which makes it less plausible that it reflects actual clinical treatment and more like a placebo effect; combined with construct-validity concerns about measuring depression via a questionnaire, this complicates interpretation.Jim Manzi on the Oregon Medicaid Study, Experimental Evidence, and Causality