A Monte Carlo Comparison of Maximum Likelihood and Minimum Chi Square Sampling Distributions in Logit Analysis

Kimberly C. Smith; N. E. Savin; Jacqueline L. Robertson

doi:10.2307/2531399

Back

A Monte Carlo Comparison of Maximum Likelihood and Minimum Chi Square Sampling Distributions in Logit Analysis

Journal article

Peer reviewed

A Monte Carlo Comparison of Maximum Likelihood and Minimum Chi Square Sampling Distributions in Logit Analysis

Kimberly C. Smith, N. E. Savin and Jacqueline L. Robertson

Biometrics, Vol.40(2), pp.471-482

06/01/1984

DOI: 10.2307/2531399

View Online

Abstract

The finite-sample properties of maximum likelihood and minimum chi square estimators in a simple dichotomous logit regression model are studied by Monte Carlo methods. Convergence of the regression coefficient test statistics to normality is slow for designs in which doses are placed asymmetrically about the ED50; skewness and bias are problems even at sample sizes of 480. Designs with doses symmetric about the ED50 can be used with reasonable confidence at moderate sample sizes. There is some evidence that maximum likelihood is preferable to minimum chi square when statistical inferences are to be made with a logit model.

Approximation

Confidence interval

Estimation bias

Estimators

Maximum likelihood estimation

Probabilities

Regression coefficients

Sample size

Skewed distribution

Statistical variance

Details

Title: Subtitle: A Monte Carlo Comparison of Maximum Likelihood and Minimum Chi Square Sampling Distributions in Logit Analysis
Creators: Kimberly C. Smith
N. E. Savin
Jacqueline L. Robertson
Resource Type: Journal article
Publication Details: Biometrics, Vol.40(2), pp.471-482
DOI: 10.2307/2531399
ISSN: 0006-341X
eISSN: 1541-0420
Publisher: Biometric Society
Number of pages: 12
Language: English
Date published: 06/01/1984
Academic Unit: Economics
Record Identifier: 9984963096102771

Metrics

1 Record Views