ERIC Number: ED426097
Record Type: RIE
Publication Date: 1999-Jan
Defining and Interpreting Suppressor Effects: Advantages and Limitations.
Lancaster, Brian P.
Suppressor effects are considered one of the most elusive dynamics in the interpretation of statistical data. A suppressor variable has been defined as a predictor that has a zero correlation with the dependent variable while still, paradoxically, contributing to the predictive validity of the test battery (P. Horst, 1941). This paper explores the three definitions of regression suppressor variables by reviewing existing literature about suppressor effects and provides a heuristic example that demonstrates how the different types of suppressor variables can be detected. Special considerations in detecting suppressor effects are discussed, along with possible limitations researchers may encounter when including suppressor variables in a statistical design. (Contains 1 figure, 4 tables, and 14 references.) (SLD)
Publication Type: Information Analyses; Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A
Note: Paper presented at the Annual Meeting of the Southwest Educational Research Association (San Antonio, TX, January 21-23, 1999).