An Exact Density-Based Empirical Likelihood Ratio Test for Paired Data.

摘要: Abstract The Wilcoxon rank-sum test and its variants are historically well-known to be very powerful nonparametric decision rules for testing no location difference between two groups given paired data versus a shift alternative. In this title, we propose new alternative empirical likelihood (EL) ratio approach the equality of marginal distributions that sampling is from continuous bivariate population. We show in various scenarios proposed exact superior classic procedures, which may break down completely or frequently inferior density-based EL test. This particularly true cases where there nonconstant under skewed. An extensive Monte Carlo study shows has excellent operating characteristics. apply analyze real medical studies.