A persistent puzzle in psychometrics has been "the measurement of change." Many in- vestigators have felt, for reasons good or bad, that their substantive questions required a measure of gain in ability or shift in attitude. "Raw change" or "raw gain" scores formed by subtracting pretest scores from posttest scores lead to fallacious conclusions, primarily be- cause such scores are systematically related to any random error of measurement. Although the unsuitability of such scores has long been discussed, they are still employed, even by some otherwise sophisticated investigators. At the end of this paper the authors argue that gain scores are rarely useful, no matter how they may be adjusted or refined. The authors also distinguish four kinds of inquiry for which such scores have been used, and con- clude that only one of these purposes is well served by any kind of gain score. This argu- ment applies not only to changes over time, but also to other differences between two vari- ables. The first part of the paper proposes superior ways of estimating true change and true resid- ual change scores. It may seem pointless to discuss such matters when in the end we rec- ommend against their use (save in a few kinds of investigation ). However, the development of formulas clarifies the model, providing a 1 Initial work on this paper was conducted under a