Methods for Testing the Difference Between Two Signal-to-Noise Ratios of Log-Normal Distributions

摘要

This study presents three methods for testing the difference between two signal-to-noise ratios (SNRs) of log-normal distributions. The proposed statistical tests were based on the generalized confidence interval (GCI) approach, the large sample (LS) approach and the method of variance estimates recovery (MOVER) approach. To compare the performance of the proposed statistical tests, a simulation study was conducted under several values of SNRs in log-normal distributions. The performance of the statistical tests was compared based on the empirical size and power of the test. The simulation results showed that the statistical test based on the GCI approach performed better than the statistical tests based on the LS and the MOVER approaches in terms of the attained nominal significance level and empirical power of the test and is thus recommended for researchers. The performance of the proposed statistical tests is also illustrated through a numerical example.