pith. sign in

arxiv: 1612.06967 · v1 · pith:WX3JNTJQnew · submitted 2016-12-21 · 🧮 math.ST · stat.TH

Note on information bias and efficiency of composite likelihood

classification 🧮 math.ST stat.TH
keywords compositelikelihoodbiascomponentinformationlikelihoodsnoteaddi-
0
0 comments X
read the original abstract

Does the asymptotic variance of the maximum composite likelihood estimator of a parameter of interest always decrease when the nuisance parameters are known? Will a composite likelihood necessarily become more efficient by incorporating addi- tional independent component likelihoods, or by using component likelihoods with higher dimension? In this note we show through illustrative examples that the an- swer to both questions is no, and indeed the opposite direction might be observed. The role of information bias is highlighted to understand the occurrence of these paradoxical phenomenon.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Composite likelihood inference for the Poisson log-normal model

    stat.CO 2024-02 unverdicted novelty 5.0

    A composite-likelihood EM algorithm with importance sampling yields computationally feasible, asymptotically valid inference for the Poisson log-normal model on moderately large multivariate count datasets.