Standard Curves for Empirical Likelihood Ratio Tests of Means

2021/05/19 by Jost Viebrock, Viebrock, Jost, Thorsten Dickhaus +1
Mathematics · #62G10 #62G15 #62G20 #FOS: Computer and information sciences #Methodology (stat.ME) #msc:62G10 #msc:62G15 #msc:62G20 #stat.ME

paper · pdf · doi:10.48550/arxiv.2105.09031

arxiv created 2021/05/19 · arxiv updated 2021/05/20

Abstract

We present simulated standard curves for the calibration of empirical likelihood ratio (ELR) tests of means. With the help of these curves, the nominal significance level of the ELR test can be adjusted in order to achieve (quasi-) exact type I error rate control for a given, finite sample size. By theoretical considerations and by computer simulations, we demonstrate that the adjusted significance level depends most crucially on the skewness and on the kurtosis of the parent distribution. For practical purposes, we tabulate adjusted critical values under several prototypical statistical models.

Related

• Adjusted empirical likelihood with high-order precision
• Curve registration by nonparametric goodness-of-fit testing
• Empirical likelihood for linear models with spatial errors
• Adjusted Empirical Likelihood for Time Series Models
• Adjusted Empirical Likelihood and its Properties