Download PDF

Volume 24, No. (1), 2014 (February)

INFLUENCE OF USING ALTERNATIVE MEANS ON TYPE-I ERROR RATE IN THE COMPARISON OF INDEPENDENT GROUPS

H. Mirtagioğlu, S. Yiğit, A. Mollaoğulları, S. Genç, M. Mendeş

H. Mirtagioğlu, S. Yiğit*, A. Mollaoğulları**, S. Genç*** and M. Mendeş****

Yüzüncüyıl University, Faculty of Agriculture, Department of Animal Science, Biometry and Genetics Unit,Van-Turkey
*Transitional Zone Agricultural Research Institute, Eskişehir,TURKEY.
**Çanakkale Onsekiz Mart University, Faculty of Art and Science, Department of Mathematics, Çanakkale-Turkey
***Ahi Evran University, Faculty of Agriculture Department of Agricultural Biotechnology, Kırşehir -Turkey
****Çanakkale Onsekiz Mart University, Department of Animal Science, Biometry and Genetics Unit, Çanakkale -Turkey
Corresponding Author: serdargenc1983@gmail.com
Page Number(s): 344-349
Published Online First: February 01, 2014
Publication Date: February 01, 2014

ABSTRACT

In this study, the effect of using trimmed, winsorized, and modified means instead of arithmetic mean on type-I error rate was investigated when the assumptions of the one-way ANOVA were not satisfied. Therefore, random numbers were generated by simulation technique from the populations distributed by Normal (0,1), Beta (5,2) and χ2 (3) for 3 and 4 groups. The results of 30 000 simulation trials demonstrated that all the means displayed similar type-I error rates when the variances were homogenous regardless of the distribution shape, sample size and the number of groups. When homogeneity of variances assumption was not satisfied, the most reliable result was obtained by using trimmed mean in terms of keeping the type-I error rate at nominal alpha level and it was followed by modified and winsorized means. The most biased results were obtained when arithmetic mean was used. 
Keywords: One-way ANOVA, Outlier, Non-normality, Homogeneity of variance, Type-I error
Open Access: This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ( https://creativecommons.org/licenses/by/4.0/).
Share:
Download Statistics
This Manuscript
Full Text
8
downloads
Indicators
Metrics

Cite Score: 1.3

JCR Year: 2025

Indexing
Status

Web of Science (SCIE)

SCOPUS (Q3)

Journal Metrics
Current

Journal Impact Factor: 0.5

HEC Category: W

ISSN Details
Verified

Print ISSN: 1018-7081

Electronic ISSN: 2309-8694

Search the Journal

Use the fields below to search for articles by Title, Author, or Keywords.

All Downloads
Full Text
63,865
downloads
Supplementary
188
downloads
© , Developed by HISOFT