On asymptotic validity of naive inference with an approximate likelihood

DOI10.1093/BIOMET/ASX002MaRDI QIDQ5384450zbMATH OpenOpenAlexFDO

Authors Helen E. Ogden

Publication date 24 June 2019

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1601.07911, https://eprints.soton.ac.uk/404352/1/ogden.pdf

zbMATH Keywords

intractable likelihoodIsing modelLaplace approximationlatent variable model

Mathematics Subject Classification ID

Point estimation (62F10) Asymptotic properties of parametric estimators (62F12) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Abstract: Many statistical models have likelihoods which are intractable: it is impossible or too expensive to compute the likelihood exactly. In such settings, a common approach is to replace the likelihood with an approximation, and proceed with inference as if the approximate likelihood were the exact likelihood. In this paper, we describe conditions on the approximate likelihood which guarantee that this naive inference with an approximate likelihood has the same first-order asymptotic properties as inference with the exact likelihood. We investigate the implications of these results for inference using a Laplace approximation to the likelihood in a simple two-level latent variable model, and using reduced dependence approximations to the likelihood in an Ising model on a lattice.

Recommendations

• Asymptotic properties of approximate Bayesian computation
• Asymptotics and the theory of inference
• Approximate likelihood inference in generalized linear latent variable models based on the dimension-wise quadrature
• A note on pseudolikelihood constructed from marginal densities
• Asymptotic normality and valid inference for Gaussian variational approximation

Cited in

(11)

• When should modes of inference disagree? Some simple but challenging examples
• Approximate likelihood inference in generalized linear latent variable models based on the dimension-wise quadrature
• Asymptotic accuracy of the saddlepoint approximation for maximum likelihood estimation
• Maximum likelihood estimation based on the Laplace approximation for p₂ network regression models
• Maximum softly-penalized likelihood for mixed effects logistic regression
• Enhanced Laplace approximation
• Approximate maximum likelihood estimation in cure models using aggregated data, with application to HPV vaccine completion
• Non-boundary covariance matrix estimation in generalized linear mixed effects models using data augmentation priors
• Inference for generalized additive mixed models via penalized marginal likelihood
• Asymptotic results for penalized quasi-likelihood estimation in generalized linear mixed models
• Asymptotics of numerical integration for two-level mixed models

This page was built for publication: On asymptotic validity of naive inference with an approximate likelihood

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5384450)