Robust Tests for the Mean Difference in Paired Data using Jackknife Resampling Technique

  • Ghufran A. Ghadhban Department of Mathematics, College of Science, Mustansiriyah University, Baghdad, Iraq
  • Huda A. Rasheed Department of Mathematics, College of Science, Mustansiriyah University, Baghdad, Iraq
Keywords: Paired t-test, Robust, Jackknife, Wilcoxon signed-rank test, Contaminated Bivariate normal, Bivariate Exponential

Abstract

     The paired sample t-test is a type of classical test statistics that is used to test the difference between two means in paired data, but it is not robust against the violation of the normality assumption. In this paper, some alternative robust tests are suggested by combining the Jackknife resampling with each of the Wilcoxon signed-rank test for small sample size and Wilcoxon signed-rank test for large sample size, using normal approximation. The Monte Carlo simulation experiments were employed to study the performance of the test statistics of each of these tests depending on the type one error rates and the power rates of the test statistics. All these tests were applied on different sample sizes generated from three distributions, represented by Bivariate normal distribution, contaminated Bivariate normal distribution, and Bivariate exponential distribution.

Published
2021-09-30
How to Cite
Ghadhban, G. A., & Rasheed, H. A. (2021). Robust Tests for the Mean Difference in Paired Data using Jackknife Resampling Technique. Iraqi Journal of Science, 62(9), 3081-3090. https://doi.org/10.24996/ijs.2021.62.9.23
Section
Mathematics