Suppressor variables in path models - Definitions and interpretations

Suppressor variables are well known in the context of multiple regression a nalysis. Using several examples, the authors demonstrate that the different forms of the suppressor phenomenon described in the literature occur not o nly in prediction equations but also in the explanatory use of multiple reg ression, including structural equations models. Moreover they show that the probability of their occurrence is relatively high in models with latent v ariables, in which the suppressed variable is corrected for measurement err ors. Special attention will be paid to the two-wave model since this is par ticularly liable to the suppressor phenomenon. The occurrence of suppressio n in structural equations models is usually not foreseen and confronts rese archers with problems of interpretation. The authors discuss definitions of the suppressor phenomenon, show how the unwary researcher can be warned ag ainst it, and present guidelines for the interpretation of the results.