ERIC Number: ED232574
Record Type: RIE
Publication Date: 1983-May
Reference Count: 0
Using Regression Analysis to Determine Inequities in Faculty Salaries. AIR 1983 Annual Forum Paper.
Suskie, Linda Michaels; Shearer, Sharon
Linear regression models that predict faculty salaries from professional and affirmative action variables were developed to validate promotion and merit criteria, set a starting salary scale, and identify possible systematic and individual salary inequities. All 377 full-time teaching faculty and librarians (309 men and 68 women) employed by a public four-year college in fall 1981 were investigated. Four stepwise multiple regression analyses were performed. Rank, age, year of appointment, department chair status, librarian status, and sex all affected salary significantly; while tenure, race, and citizenship did not. Contrary to hypothesis, removing rank and tenure from the model did not unmask a sex effect. The uses of regression models in studying faculty salaries are discussed, as are the following five weaknesses: (1) the validity of the model is affected by the choice of variables, (2) variables of interest may be difficult to operationalize, (3) regression analysis assumes all data are linear, (4) regression models with a large number of predictors have relatively poor power, and (5) intercorrelations among the independent variables may mask the true relationship between the variables and salary. (Author/SW)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: AIR Forum
Note: Paper presented at the Annual Forum of the Association for Institutional Research (23rd, Toronto, Ontario, May 23-26, 1983).