Test for homogeneity with unordered paired observations

DOI10.1214/21-EJS1817zbMATH Open1471.62263arXiv1905.01402MaRDI QIDQ2044352FDOQ2044352

Authors: Jiahua Chen, Jing Qin, Tao Yu, Pengfei Li 

Publication date: 9 August 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: In some applications, an experimental unit is composed of two distinct but related subunits. The response from such a unit is $(X_1,X_2)$ but we observe only $Y_1=min{X}_1,X_2$ and $Y_2=max{X}_1,X_2$, i.e., the subunit identities are not observed. We call $(Y_1,Y_2)$ unordered paired observations. Based on unordered paired observations ${(Y_{1i},Y_{2i})}_{i=1}^n$, we are interested in whether the marginal distributions for $X_1$ and $X_2$ are identical. Testing methods are available in the literature under the assumptions that $Var(X_1)=Var(X_2)$ and $Cov(X_1,X_2)=0$. However, by extensive simulation studies, we observe that when one or both assumptions are violated, these methods have inflated type I errors or much lower powers. In this paper, we study the likelihood ratio test statistics for various scenarios and explore their limiting distributions without these restrictive assumptions. Furthermore, we develop Bartlett correction formulae for these statistics to enhance their precision when the sample size is not large. Simulation studies and real-data examples are used to illustrate the efficacy of the proposed methods.

Full work available at URL: https://arxiv.org/abs/1905.01402

Recommendations

• Statistical inference in the case of unordered pairs
• Testing against uniform stochastic ordering with paired observations
• Testing marginal homogeneity of a continuous bivariate distribution with possibly incomplete paired data
• Nonparametric tests of population differences and estimation of the probability of misidentification with unidentified paired data
• Two Statistics for Unconditional Exact Tests in Matched-Pairs Design

zbMATH Keywords

Bartlett correctionlikelihood ratio testtwo-sample testadjusted limiting distributioncorrelated unordered pairs

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Asymptotic distribution theory in statistics (62E20) Asymptotic properties of parametric tests (62F05)

Cites Work

• An introduction to copulas.
• Likelihood ratio tests and singularities
• A GENERAL METHOD FOR APPROXIMATING TO THE DISTRIBUTION OF LIKELIHOOD RATIO CRITERIA
• On the level-error after Bartlett adjustment of the likelihood ratio statistic
• Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests Under Nonstandard Conditions
• Title not available (Why is that?)
• On the Distribution of the Likelihood Ratio
• Title not available (Why is that?)
• Hypothesis test for normal mixture models: the EM approach
• Note on the Consistency of the Maximum Likelihood Estimate
• A modified likelihood ratio test for homogeneity in finite mixture models
• The likelihood ratio test for homogeneity in finite mixture models
• Tuning the EM-test for finite mixture models
• Title not available (Why is that?)
• Marginal likelihood, conditional likelihood and empirical likelihood: Connections and applications
• Convergence rates of parameter estimation for some weakly identifiable finite mixtures
• Correlation Analysis of Extreme Observations from a Multivariate Normal Distribution
• Singularity structures and impacts on parameter estimation in finite mixtures of distributions
• Local tests for identifying anisotropic diffusion areas in human brain with DTI
• A New Nuisance-Parameter Elimination Method With Application to the Unordered Homologous Chromosome Pairs Problem
• Nonparametric tests of population differences and estimation of the probability of misidentification with unidentified paired data
• On determining the parental origins of homologous chromosomes

Cited In (2)

• A mixture distribution approach for assessing genetic impact from twin study
• Statistical inference in the case of unordered pairs

This page was built for publication: Test for homogeneity with unordered paired observations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2044352)