A technique for producing a double-entry expectancy nomograph from observed proportions without distributional assumptions

A procedure for smoothing the proportions of a double-entry expectancy table is described. The product of the procedure is a nomograph from which can be read expectancies from combinations of values of two predictor variables. The nomograph might be used in admissions advising or in establishing standards for the admission of freshman students. The procedure is used to construct nomographs for predicting proportions of freshman-year grade point averages greater than or equal to 2.0 and for proportions greater than or equal to 3.0 from high school class percentile ranks and ACT composite scores for a sample of first-time freshmen. Effects of sample size and of the minimum size of groups of students used in estimating nomograph curves on the stability of the curves are examined. Suggestions for additional work on deriving expectancy nomographs are given.Presented at the Thirty-First Annual Forum of the Association for Institutional Research, San Francisco, May 26–29, 1991.