Existence of Maximum Likelihood Estimates in Regression Models for Grouped and Ungrouped Data
- 1 September 1986
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 48 (1) , 100-106
- https://doi.org/10.1111/j.2517-6161.1986.tb01394.x
Abstract
SUMMARY: In general, concavity of the log likelihood alone does not imply that the MLE exists always. For a class of linear regression models for grouped and ungrouped data, a necessary and sufficient condition is obtained for the existence of the maximum likelihood estimator. This condition has an intuitively simple interpretation. Further, it turns out that there are similar necessary and sufficient conditions for the existence of maximum likelihood estimates for a number of other non-linear models such as Cox's Regression Model. For a given set of data, these conditions may be verified by Linear Programming Methods.This publication has 9 references indexed in Scilit:
- On the existence of maximum likelihood estimates in logistic regression modelsBiometrika, 1984
- A Note on Maximum Likelihood Estimation for Regression Models Using Grouped DataJournal of the Royal Statistical Society Series B: Statistical Methodology, 1981
- On the Existence of Maximum Likelihood Estimators for the Binomial Response ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1981
- Concavity of the Log LikelihoodJournal of the American Statistical Association, 1981
- Algorithm AS 125: Maximum Likelihood Estimation for Censored Exponential Survival Data with CovariatesJournal of the Royal Statistical Society Series C: Applied Statistics, 1978
- Covariance Analysis of Censored Survival DataPublished by JSTOR ,1974
- Regression Models and Life-TablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1972
- Convex AnalysisPublished by Walter de Gruyter GmbH ,1970