Validity characterises the extent to which a measurement procedure is capable of measuring what it is supposed to measure. Normally, the term “validity” is used in situations where measurement is indirect, imprecise and cannot be precise in principle, e.g. in psychological IQ tests purporting to measure intellect. (In direct measurements of physical quantities – e.g. length, duration, weight – the concept of “accuracy” is normally used rather than “validity”.)
To establish validity, various statistical techniques and concepts are used: Pearson correlation coefficient (to quantify correspondence between measurements and and an accepted “true” value – e.g. correlation between SAT scores and subsequent college grades); factor analysis (to establish latent interrelation between variables), regression .
For different categories of validity in psychometrics see face validity , content validity , concurrent validity , predictive validity , construct validity , convergent validity , divergent validity .