Saddlepoint approximations for likelihood ratio like statistics with applications to permutation tests

DOI10.1214/11-AOS945zbMATH Open1246.62121arXiv1203.3106OpenAlexW3102469887MaRDI QIDQ450004FDOQ450004

John Robinson, John Kolassa

Publication date: 3 September 2012

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We obtain two theorems extending the use of a saddlepoint approximation to multiparameter problems for likelihood ratio-like statistics which allow their use in permutation and rank tests and could be used in bootstrap approximations. In the first, we show that in some cases when no density exists, the integral of the formal saddlepoint density over the set corresponding to large values of the likelihood ratio-like statistic approximates the true probability with relative error of order $1/n$. In the second, we give multivariate generalizations of the Lugannani--Rice and Barndorff-Nielsen or $r^{*}$ formulas for the approximations. These theorems are applied to obtain permutation tests based on the likelihood ratio-like statistics for the $k$ sample and the multivariate two-sample cases. Numerical examples are given to illustrate the high degree of accuracy, and these statistics are compared to the classical statistics in both cases.

Full work available at URL: https://arxiv.org/abs/1203.3106

Recommendations

• Saddlepoint approximations to the two-sample permutation tests
• Saddlepoint approximation for two sample linear rank tests
• Saddlepoint \(p\)-values for two-sample bivariate tests
• Saddlepoint \(p\)-values for group of linear rank tests
• Testing for independence: saddlepoint approximation to associated permutation distributions

zbMATH Keywords

large deviationsrandomization testsnonparametric tests

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Large deviations (60F10) Estimation in multivariate analysis (62H12)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Asymptotic expansions for the power of distribution free tests in the one-sample problem
• Title not available (Why is that?)
• Title not available (Why is that?)
• On large deviations for sums of random vectors in \(R_ k\).
• Fully symmetric interpolatory rules for multiple integrals over hyper-spherical surfaces
• Saddlepoint approximations and tests based on multivariate \(M\)-estimates.
• On the bootstrap saddlepoint approximations
• On approximating probabilities for small and large deviations in \(R^{d1}\)

Cited In (10)

• Title not available (Why is that?)
• Saddlepoint approximations for rank‐invariant permutation tests and confidence intervals with interval‐censoring
• A new permutation test statistic for complete block designs
• A new permutation test statistic for K‐sample multivariate designs
• Saddlepoint method for obtaining tail probability of Wilk's likelihood ratio test
• RELATIVE ERROR ACCURATE STATISTIC BASED ON NONPARAMETRIC LIKELIHOOD
• Nonparametric tests for multi-parameter \(M\)-estimators
• General Saddlepoint Approximation for Testing Separate Location-Scale Families of Hypotheses
• A Proof of the Asymptotic Equivalence of Two-Tail Probability Approximations
• A Conditional Saddlepoint Approximation for Testing Problems

Uses Software

• PATSYM
• bootlib

This page was built for publication: Saddlepoint approximations for likelihood ratio like statistics with applications to permutation tests

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q450004)