The Comparison of two Nonparametric Tests in some Distributions

• 발행기관: 한국자료분석학회
• 저자명: 박찬근(Chan Keun Park)
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.8 No.3, 901~911쪽, 전체 11쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2006.06.30

영문 초록

We Compare powers of the nonparametric tests, Mann-Whitney test and Median test, under a variety of population distributions using a simulation study. Both tests require that the two underlying populations have the same variance, but this assumption was relaxed in the comparisons. We consider the following types of distributions : Normal, Uniform, Exponential, and Cauchy. Also, to investigate th effect of location shifts in mixture distribution, we use the mixture of N(0,1) and N(3,36) Each test is performed 5,000 times under the same conditions.

목차

1. Introduction

2. Design of Study

3. Results

4. Conclusions and Further Research

References

키워드

Mann-Whitney test Median test Normal Uniform Exponential Cauchy Mixed Normal