The Development of Confidence Interval of Different Median for Two Population with Free-distributions by Price Bonett Bootstrap-t Method

Article Sidebar

PDF
Published: Feb 6, 2019
Keywords:
Coverage Probability Average Length Median Bootstrap

Main Article Content

Anurak Tongkaw
Department of General Education, Faculty of Hospitality Industry, Dusit Thani College Pattaya, Chon Buri

Abstract

The purposes of this study were to develop a confidence interval of different medians for two populations using Free-distributions by Price Bonett Boostrap-t method and to compare the performance of the proposed procedure with other existing methods. The Monte Carlo Simulation Technique was performed 5,000 times repeatedly when calculating median confidence intervals using the bootstrap technique. The rounds of random sampling with the bootstrap method were 5,000 times. The simulation involved both data from the population with free-distributions and the size of each sample by using the R program. The results indicated that the Price Bonett Boostrap-t method performance was better than the Price Bonett method and Percentile Bootstrap method, considering 17 from the total 24 situations of this study.

Article Details

Issue
Vol. 29 No. 1 (2019): January-March, 2019
Section
Applied Science Research Articles

The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.

References

[1] S. Naksawat, S. Chadcham, and P. Makmee, “Development of the human capital assessment criteria for industrial sector,” Research Methodology and Cognitive Science, vol. 13, no. 2, pp. 90–108, 2015.

[2] K. Vanichbuncha, Principles of Statistics. Bangkok: Chulalongkorn University Press, 2010 (in Thai).

[3] R. M. Price and D. G. Bonett, “Distribution-free confidence intervals for difference and ratio of medians,” Journal of Statistical Computation and Simulation, vol. 72, no. 2, pp 119–124. 2002.

[4] B. Efron and R. J. Tibshiran, An Introduction to the Bootstrap. Boca Raton: Chapman & Hall. New York, 1994.

[5] P. Aiemsuwan, “Confidence intervals for a coefficient of quartile variation with Bonett method and Bootstrap method,” The Journal of KMUTNB, vol. 25, no. 1, pp. 161–168. 2015 (in Thai).

[6] A. Tongkaw, “Confidence interval of one population variance by Bonett bootstrap-t method for non-normal distributions,” RMUTSB Academic Journal, vol. 5, no. 1, pp. 11–19, 2017.

[7] A. Tongkaw, “The development of confidence interval for a one population variance by adjust hummel with Bootstrap-t method,” presented at the 4th NEU National and International Conference, Khon Kaen ,Thailand, july 21, 2017.

[8] A. Tongkaw and V. Pongsakchat, “Confidence intervals for a coefficient of quartile variation with Bootstrap method,” presented at International Conference on Applied Statistics, Khon Kaen, Thailand, May 21–24, 2014.

[9] B. E. Smith and F. J. Merceret, “The lognormal distribution,” The College Mathematics Journal, vol. 31, no. 4, pp. 259–261, 2000.