Journal of Integrative Natural Science (통합자연과학논문집)

The Basic Science Institute Chosun University (조선대학교 기초과학연구원)
권호 표지
DOI QR코드

DOI QR Code

Comparison of the Power of Bootstrap Two-Sample Test and Wilcoxon Rank Sum Test for Positively Skewed Population

  • Heo, Sunyeong (Department of statistics, Changwon National University)
  • Received : 2022.02.21
  • Accepted : 2022.03.18
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This research examines the power of bootstrap two-sample test, and compares it with the powers of two-sample t-test and Wilcoxon rank sum test, through simulation. For simulation work, a positively skewed and heavy tailed distribution was selected as a population distribution, the chi-square distributions with three degrees of freedom, χ23. For two independent samples, the fist sample was selected from χ23. The second sample was selected independently from the same χ23 as the first sample, and calculated d+ax for each sampled value x, a randomly selected value from χ23. The d in d+ax has from 0 to 5 by 0.5 interval, and the a has from 1.0 to 1.5 by 0.1 interval. The powers of three methods were evaluated for the sample sizes 10,20,30,40,50. The null hypothesis was the two population medians being equal for Bootstrap two-sample test and Wilcoxon rank sum test, and the two population means being equal for the two-sample t-test. The powers were obtained using r program language; wilcox.test() in r base package for Wilcoxon rank sum test, t.test() in r base package for the two-sample t-test, boot.two.bca() in r wBoot pacakge for the bootstrap two-sample test. Simulation results show that the power of Wilcoxon rank sum test is the best for all 330 (n,a,d) combinations and the power of two-sample t-test comes next, and the power of bootstrap two-sample comes last. As the results, it can be recommended to use the classic inference methods if there are widely accepted and used methods, in terms of time, costs, sometimes power.

Keywords

References

  1. Gibbons J. D., "Nonparametric Statistics: An Introduction", Sage University Paper series on Quantitiative Application in the Social Science, 07-090, Newbury Park, CA; Sage, 1993.
  2. Conover, W. J., Practical Nonparametric Statistics (2nd ed), New York: Wiley, 1980.
  3. Sprent, P. and Smeeton, N. C., Applied Nonparametric Statistical Methods, 3rd ed., Chapman & Hall/CRC, London, 2001.
  4. Mooney, C. Z. and Duval, R. D., "Bootstrapping: A Nonparametric Approach to Statistical Inference", Sage University Paper series on Quantitiative Application in the Social Science, 07-095, Newbury Park, CA; Sage, 1993.
  5. Efron, B., "Bootstrap methods: Another look at the jackknife." Annals of Statistics, Vol. 7, pp. 1-26, 1979. https://doi.org/10.1214/aos/1176344552
  6. Efron, B. and Tibshirani, R. "Bootstrap methods for Standard errors, confidence intervals, and other measures of statistical accuracy", Statistical Science 1: pp. 54-77, 1986. https://doi.org/10.1214/ss/1177013815
  7. Good, P. I., Resampling Methods: A Practical Guide to Data Analysis, Birkha.. user, Boston, 1999.
  8. Efron, B., The jackknife, the bootstrap, and other resampling plans, Philadelphia: Society for Industrial and Applied Mathematics, 1982.
  9. Efron, B. and Tibshirani, R. An introduction to the Bootstrap, London, Chapman & Hill, 1993.
  10. Johnson, R. W., "An introduction to the bootstrap", Teaching Statistics, Vol. 23, No. 2, pp. 49-54, 2001. https://doi.org/10.1111/1467-9639.00050
  11. Bruce, P., Bruce, A., and Gedeck, P., Practical Statistics for Data Scientists: 50+ Essential Concepts Using R and Python 2nd ed., O'Reilly Median, 2020.