Quantcast
Channel: 國立中央大學 National Central University- RSS訂閱
Viewing all articles
Browse latest Browse all 7082

A two-sample variability test

$
0
0
統計研究所
學術演講

主講人:
黃子銘教授 (政治大學統計系)
題    目:A two-sample variability test
時    間:100年09月27日(星期二)上午11:00 ~ 11:50
地    點:中央大學鴻經館 116 室

茶    會:上午 10:30 ~11:00
地 點:鴻經館 510 室


ABSTRACT
Moses (1963) proposed a distribution-free variability test for the two-sample case. The test is robust and does not require estimating the location parameters for both samples or the difference between the location parameters. A disadvantage of Moses´s test is that it makes use of only about half of the data, which results in a low power performance when the sizes for both samples are small. A modified test is proposed to make use of all data to compute the test statistic. Simulation results will be presented.

Viewing all articles
Browse latest Browse all 7082

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>