This methodological note illustrates how a commonly used calculation of the Delta-p statistic is inappropriate for categorical independent variables, and this note provides users of logistic regression with a revised calculation of the Delta-p statistic that is more meaningful when studying the differences in the predicted probability of an…

This study used Tobit analysis to estimate retention probabilities and credit hours at two universities. Tobit was judged as appropriate for this problem because it recognizes the lower bound of zero on credit hours and incorporates this bound into parameter estimates and forecasts. Models are estimated for credit hours in a single year and…

A study compared approaches to assessing the influence of student financial aid on within-year persistence of traditional college students. Results indicated that models including tuition were better predictors of persistence, that use of multiple approaches provided more insight into policy's role, and that tuition charges had a consistent…

A study used a multivariate approach to assessing college departmental excellence. Factor analysis identified three potentially useful factor clusters ("faculty research,""input," and "student") and seven indicators based on those clusters. Indicators combining faculty research and input and combining all three clusters were found to be the best…

Universities attempt to hire the highest quality faculty they can, but they are not always successful at retaining them. Furthermore, some faculty members who do remain may not function as engaging colleagues who make others want to stay. This study investigates why some faculty members leave and why others stay by illuminating the complexities of…

A study using discriminant analysis to correct bias in predicting faculty rank is reported. Findings concerning the relationship of prediction error and gender and suggestions for use of the results to study salary-bias problems are also discussed. (Author/MSE)

Two studies illustrate how omitting faculty rank as a predictor variable from gender equity studies of faculty salaries can lead to incorrect conclusions about gender discrimination. One uses hypothetical data constructed so there is no gender difference in salary, but omission of academic rank skews the results. The second uses data from a…

Survival analysis was used to model retention of 8,867 undergraduate students at Oregon State University from 1991 to 1996. Attrition increased with age and nonresident status; it decreased with higher high-school and first-quarter grades, and attendance in a freshman orientation course. Retention was also associated with race/ethnicity and…