Home | Business News | Browse by Publication | I | International Advances in Economic Research

Predicting MBA no-shows and graduation success with discriminate analysis.

Article Excerpt
Abstract

This paper uses discriminate analysis to examine five years of MBA admission records in order to separate no-shows from the successful program graduates. The study used traditional numeric data such as age, length of time with current employer, undergraduate GPA and GMAT scores--as well as dummy variables for sex, full- or part-time status, race, the public or private nature of the undergraduate institution, and in-state tuition eligibility. The analysis correctly separated the no-shows with a 94.2 percent classification rate based entirely on the use of dummy variables. Unlike other studies, undergraduate GPAs, GMAT scores, and other numeric variables played no role in the final classification. The results suggest that more attention be given to the use of dummy variables when it comes to predicting the success of MBA program graduates. (JEL 121)

**********

Introduction

When students seek admission to an MBA program, they presumably do so with the expectation that they will eventually graduate. At the same time, the graduate program administrator wants to do everything possible to make sure that the students have the appropriate background, skills, and motivation to succeed in the program. Accordingly, applicants are usually required to submit a variety of materials--ranging from GMAT scores to undergraduate GPAs to letters of reference--in order to gain admission to their program of choice. Some of the requirements, such as GPAs and GMATs, are usually in the form of threshold requirements. Other submissions, such as letters of reference, are more subjective. Even other information, such as place of residence, age, sex, or previous military experience, is more demographic. Collectively, the graduate program administrator hopes that the data are sufficiently complete to admit only those students who stand a reasonable chance of completing the degree.

Despite these precautions, some students do not complete the program at all, some do so only after a lengthy delay, and others never even show up for classes. While there may be a variety of legitimate reasons for these outcomes, it is reasonable to ask if there might have been some subtle indicators of success or failure that were not immediately evident during the admissions phase. Accordingly, the purpose of this study is to see whether information only available at the time of admission to the MBA program can be used to correctly categorize applicants into two groups--no-shows and those who successfully graduate.

The factors indicating graduate student outcomes identified in this paper will assist the MBA Director at Northern Kentucky University in predicting a student's successful completion of the program. An analysis of the data will also help the graduate program administrator evaluate the usefulness of the information currently being collected, as well as establish a rationale for using and retaining it. Finally, the results of this study may also be helpful to graduate program directors at other universities who face the same problem.

Literature Review

There have been numerous studies conducted for the purpose of identifying factors capable of predicting a student's success in a particular academic program. Previous studies of this general topic--predicting success rates of students in MBA or graduate management programs--can be sorted according to the research method employed in the study into three general categories. The categories involve the use of regression analysis, multiple discriminant analysis, and neural networks.

Regardless of the methodology used, the most important variables uncovered by these investigations were the applicant's GMAT score and undergraduate GPA as minimum admission requirements into a graduate business program [Benson, 1983; Carver and King, 1994; Deckro and Woundedberg, 1977;...

View this article FREE - Now for a Limited Time, try Goliath Business News
Free for 3 Days!