Choosing between logistic regression and discriminant analysis

S. James Press, Sandra Wilson

Expert InsightsPublished 1979

The problem of classifying an observation into one of several populations is discriminant analysis, or classification. Relating qualitative variables to other variables through a logistic functional form is often called logistic regression. It is well known that if the populations are normal and if they have identical covariance matrices, discriminant analysis estimators are to be preferred over those generated by logistic regression for the discriminant analysis problem. This situation is atypical, however, since in most discriminant analysis applications, at least one variable is qualitative (ruling out multivariate normality). Under nonnormality, we prefer the logistic regression model with maximum likelihood estimators for solving both the discriminant analysis problem and the logistic regression problem. The authors summarize the related arguments and report on their own supportive empirical studies.

Document Details

  • Copyright: RAND Corporation
  • Availability: Web Only
  • Year: 1979
  • Pages: 17
  • Document Number: P-6277

Citation

Chicago Manual of Style

Press, S. James and Sandra Wilson, Choosing between logistic regression and discriminant analysis. Santa Monica, CA: RAND Corporation, 1979. https://www.rand.org/pubs/papers/P6277.html.
BibTeX RIS

This publication is part of the RAND paper series. The paper series was a product of RAND from 1948 to 2003 that captured speeches, memorials, and derivative research, usually prepared on authors' own time and meant to be the scholarly or scientific contribution of individual authors to their professional fields. Papers were less formal than reports and did not require rigorous peer review.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.