Translator Disclaimer
July, 1973 Log-Linear Models for Frequency Data: Sufficient Statistics and Likelihood Equations
Shelby J. Haberman
Ann. Statist. 1(4): 617-632 (July, 1973). DOI: 10.1214/aos/1176342458

Abstract

A general model is proposed for analysis of frequency tables. This model includes conventional log-linear models for complete and incomplete factorial tables and logit models for quantal response analysis. By use of coordinate-free methods of linear algebra and differential calculus, complete minimal sufficient statistics and likelihood equations for the maximum likelihood estimate are derived. The maximum likelihood estimate is shown to be unique if it exists, and necessary and sufficient conditions are given for its existence.

Citation

Download Citation

Shelby J. Haberman. "Log-Linear Models for Frequency Data: Sufficient Statistics and Likelihood Equations." Ann. Statist. 1 (4) 617 - 632, July, 1973. https://doi.org/10.1214/aos/1176342458

Information

Published: July, 1973
First available in Project Euclid: 12 April 2007

zbMATH: 0261.62005
MathSciNet: MR383620
Digital Object Identifier: 10.1214/aos/1176342458

Subjects:
Primary: 62B99
Secondary: 62F10

Rights: Copyright © 1973 Institute of Mathematical Statistics

JOURNAL ARTICLE
16 PAGES


SHARE
Vol.1 • No. 4 • July, 1973
Back to Top