A Simple and Accurate Method for Approximate Conditional Inference Applied to Exponential Family Models
- 1 January 1996
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 58 (1) , 177-188
- https://doi.org/10.1111/j.2517-6161.1996.tb02074.x
Abstract
SUMMARY: A simple method for approximate conditional inference is described. The methodology is applied to natural exponential family models where it is shown to provide accurate approximations to fully conditional estimates. The approximation technique can be applied much more generally than in this particular class of models. The technique depends only on the construction of certain 'projected scores' derived from higher order likelihood derivatives and their covariances and so can be used in many problems where it is relevant to control for the estimation of nuisance parameters.This publication has 16 references indexed in Scilit:
- Semiparametric Estimation in the Rasch Model and Related Exponential Response Models, Including a Simple Latent Class Model for Item AnalysisJournal of the American Statistical Association, 1991
- Generalized Linear ModelsPublished by Springer Nature ,1989
- The Theory and Applications of Statistical Inference FunctionsPublished by Springer Nature ,1988
- Computing Distributions for Exact Logistic RegressionJournal of the American Statistical Association, 1987
- Efficiency of the Conditional Score in a Mixture SettingThe Annals of Statistics, 1983
- Conditional score functions: Some optimality resultsBiometrika, 1982
- Theoretical StatisticsPublished by Taylor & Francis ,1979
- The Efficiency of Cox's Likelihood Function for Censored DataJournal of the American Statistical Association, 1977
- Conditional likelihood and unconditional optimum estimating equationsBiometrika, 1976
- Marginal likelihoods based on Cox's regression and life modelBiometrika, 1973