Quantifying nuisance parameter effects via decompositions of asymptotic refinements for likelihood-based statistics

DOI10.1016/J.JSPI.2015.03.006zbMATH Open1326.62045arXiv1503.05900OpenAlexW2963039367MaRDI QIDQ894780FDOQ894780

G. Alastair Young, Thomas J. Diciccio, Todd A. Kuffner

Publication date: 23 November 2015

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Abstract: Accurate inference on a scalar interest parameter in the presence of a nuisance parameter may be obtained using an adjusted version of the signed root likelihood ratio statistic, in particular Barndorff-Nielsen's $R^{*}$ statistic. The adjustment made by this statistic may be decomposed into a sum of two terms, interpreted as correcting respectively for the possible effect of nuisance parameters and the deviation from standard normality of the signed root likelihood ratio statistic itself. We show that the adjustment terms are determined to second-order in the sample size by their means. Explicit expressions are obtained for the leading terms in asymptotic expansions of these means. These are easily calculated, allowing a simple way of quantifying and interpreting the respective effects of the two adjustments, in particular of the effect of a high dimensional nuisance parameter. Illustrations are given for a number of examples, which provide theoretical insight to the effect of nuisance parameters on parametric inference. The analysis provides a decomposition of the mean of the signed root statistic involving two terms: the first has the property of taking the same value whether there are no nuisance parameters or whether there is an orthogonal nuisance parameter, while the second is zero when there are no nuisance parameters. Similar decompositions are discussed for the Bartlett correction factor of the likelihood ratio statistic, and for other asymptotically standard normal pivots.

Full work available at URL: https://arxiv.org/abs/1503.05900

Recommendations

• scientific article; zbMATH DE number 720756
• scientific article; zbMATH DE number 1086064
• An empirical adjustment to the likelihood ratio statistic
• scientific article; zbMATH DE number 3998953
• scientific article; zbMATH DE number 472939

zbMATH Keywords

profile likelihoodancillary statisticBartlett correctiondecompositionexponential familynuisance parameteradjusted signed root likelihood ratioCornish-Fisher

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Asymptotic distribution theory in statistics (62E20) Asymptotic properties of parametric tests (62F05) Parametric tolerance and confidence regions (62F25)

Cites Work

• Bootstrap confidence intervals. With comments and a rejoinder by the authors
• Modified profile likelihoods in models with stratum nuisance parameters
• Title not available (Why is that?)
• On a formula for the distribution of the maximum likelihood estimator
• An approximation to the modified profile likelihood function
• Title not available (Why is that?)
• Applied Asymptotics
• A GENERAL METHOD FOR APPROXIMATING TO THE DISTRIBUTION OF LIKELIHOOD RATIO CRITERIA
• Title not available (Why is that?)
• Title not available (Why is that?)
• Simple and accurate one-sided inference from signed roots of likelihood ratios
• Likelihood methods in statistics
• Title not available (Why is that?)
• Better Bootstrap Confidence Intervals
• An explicit large-deviation approximation to one-parameter tests.
• Accurate parametric inference for small samples
• Parametric bootstrapping with nuisance parameters
• Conditional properties of unconditional parametric bootstrap procedures for inference in exponential families
• Title not available (Why is that?)
• Title not available (Why is that?)
• Stable and invariant adjusted directed likelihoods
• Title not available (Why is that?)
• Miscellanea. The directed modified profile likelihood in models with many nuisance parameters
• Routes to higher-order accuracy in parametric inference
• Tail probabilities from observed likelihoods
• Effects of the reference set on frequentist inferences
• Quantifying nuisance parameter effects via decompositions of asymptotic refinements for likelihood-based statistics

Cited In (5)

• Title not available (Why is that?)
• Quantifying nuisance parameter effects via decompositions of asymptotic refinements for likelihood-based statistics
• Reducing the sensitivity to nuisance parameters in pseudo‐likelihood functions
• The formal relationship between analytic and bootstrap approaches to parametric inference
• Likelihood, Replicability and Robbins' Confidence Sequences

This page was built for publication: Quantifying nuisance parameter effects via decompositions of asymptotic refinements for likelihood-based statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q894780)