SplitHalfReliabilität

Split-half reliability is a method used in psychometrics to estimate the internal consistency of a test or questionnaire. It assesses the extent to which different items within a measure that are intended to tap into the same construct produce similar scores. The procedure involves dividing a test into two equivalent halves and then correlating the scores on these two halves. A common way to do this is by splitting the test into odd-numbered items and even-numbered items. A high correlation between the scores on the two halves suggests that the test is internally consistent. However, this method provides an underestimate of the total test's reliability because it essentially treats the two halves as separate tests, each with less items than the full test. To correct for this attenuation, the Spearman-Brown prophecy formula is typically applied, which extrapolates the reliability of the whole test from the correlation of the two halves. A higher split-half reliability coefficient, after the correction, indicates greater internal consistency of the measurement instrument. This method is particularly useful for measures where administering the same test multiple times is not feasible.