ERIC Number: ED330726
Record Type: RIE
Publication Date: 1991-Jan
Reference Count: 0
Conceptual Underpinnings and Historical Perspectives on Evaluating Test Bias.
Palomares, Ronald S.; Friedrich, Katherine R.
Various classical approaches to evaluating test bias are reviewed, and their conceptual underpinnings are discussed. Bias is examined as it relates to predictive validity, rather than construct validity. One of the first test bias models was developed by T. A. Cleary (1968). Cleary's work with test bias and regression stimulated others to develop related methods. One of the first to do so was R. L. Thorndike. Thorndike actually developed a selection model, not a definition of test bias, because his model imposes a method to ensure the fair use of a test in selection procedures. The restatement of the models of Cleary and Thorndike by R. B. Darlington (1971) is also appropriate for ensuring fair selection, but not for the determination of test bias. The definition of bias of A. R. Jensen (1980) is inclusive and gives a clear statistical definition of bias in that it is, in fact, the definition of a biased predictor. A test is considered biased with respect to predictive validity when there is a significant difference between the majority and minority groups as found between the slopes, intercepts, or standard errors of estimates. The emphasis is on the predictive ability of the test, and not some internal property of the test itself. Five graphs illustrate the text. (SLD)
Publication Type: Information Analyses; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the Southwest Educational Research Association (San Antonio, TX, January 24-26, 1991).