Computationally efficient likelihood inference in exponential families when the maximum likelihood estimator does not exist

DOI10.1214/21-EJS1815zbMath1471.62427arXiv1803.11240WikidataQ115517649 ScholiaQ115517649MaRDI QIDQ2044372

Charles J. Geyer, Daniel J. Eck

Publication date: 9 August 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.11240

zbMATH Keywords

logistic regressiongeneralized linear modelscomplete separationcompletion of exponential families

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Generalized linear models (logistic models) (62J12)

Related Items (2)

Confidence intervals for discrete log-linear models when MLE does not exist ⋮ glmdr

Uses Software

• ergm
• rcdd
• GitHub

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Maximum likelihood estimation in log-linear models
• Existence of MLEs for discrete linear exponential models
• Closures of exponential families
• Likelihood inference in exponential families and directions of recession
• On the geometry of discrete exponential families with application to exponential random graph models
• The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
• Approximating faces of marginal polytopes in discrete hierarchical models
• Polyhedral conditions for the nonexistence of the MLE for hierarchical log-linear models
• Generalized maximum likelihood estimates for exponential families
• Instability, Sensitivity, and Degeneracy of Discrete Exponential Families
• On the existence of maximum likelihood estimates in logistic regression models
• On limiting towards the boundaries of exponential families
• A note on A. Albert and J. A. Anderson's conditions for the existence of maximum likelihood estimates in logistic regression models
• Information projections revisited
• The compactification of generalized linear models
• Convex cores of measures on R d
• Aster models for life history analysis
• Convex Analysis

This page was built for publication: Computationally efficient likelihood inference in exponential families when the maximum likelihood estimator does not exist