The Spearman-Brown prophecy formula provides a rough estimate of how much the reliability of test scores would increase or decrease if the number of observations or items in a measurement instrument were increased or decreased. This formula is called the Spearman-Brown (S-B) formula because the idea was introduced by both C. Spearman and W. Brown in articles they wrote in 1910. This entry demonstrates two ways to calculate the S-B formula and show how the predictions in score reliability typically vary with increases or decreases in the numbers of items on a test.

The S-B formula is commonly used to estimate the full-test reliability from the half-test correlation when calculating split-half reliability. Split-half reliability is an internal-consistency strategy for estimating reliability that is similar to the ...