A general class of models for discrete multivariate data
- 1 January 1986
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 15 (2) , 405-424
- https://doi.org/10.1080/03610918608812515
Abstract
A very general class of models for discrete data is introduced that includes log-linear, linear, and product models as special cases. Maximum likelihood equations are developed to yield a Fisher scoring algorithm for fitting the models to both complete and incomplete data. Two examples serve to underscore the usefulness of these models.Keywords
This publication has 10 references indexed in Scilit:
- The Estimation of Dental Caries Incidence in the Presence of Diagnostic ErrorBiometrics, 1979
- Product Models for Frequency Tables Involving Indirect ObservationThe Annals of Statistics, 1977
- Two-Dimensional Contingency Tables with Both Completely and Partially Cross-Classified DataPublished by JSTOR ,1974
- The Analysis of Partially Categorized Contingency DataBiometrics, 1974
- Log-Linear Models for Frequency Tables Derived by Indirect Observation: Maximum Likelihood EquationsThe Annals of Statistics, 1974
- Maximum Likelihood Estimation with Incomplete Multinomial DataJournal of the American Statistical Association, 1971
- The Unrelated Question Randomized Response Model: Theoretical FrameworkJournal of the American Statistical Association, 1969
- Maximum Likelihood in Three-Way Contingency TablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1963