Reliability (psychometric)

In psychometrics reliability is the accuracy of a measure. Reliability does not imply validity. That is, a reliable measure is measuring something accurately, but not necessarily what it is supposed to be measuring. For example, some reliable standardized tests of achievement in mathematics are reasonably suspected of actually being measures of linguistic ability.

Reliability may be assessed mathematically. Internal consistency may be assessed by correlating performance on two halves of a test (split-half reliability); the value of the Pearson product-moment correlation coefficient is adjusted with the Spearman-Brown prediction formula[?] to correspond to the correlation between two full-length tests. A commonly used measure is Cronbach's α, which is equivalent to the mean of all possible split-half coefficients. Stability over repeated measures is assessed with the Pearson coefficient, as is the equivalence of different versions of the same measure (different forms of an intelligence test, for example). Other measures are also used.

Reliability may be improved without formal psychometric analysis. For example, increasing the number of significant figures[?] in a reliable measure will make it more reliable.