Linear Hypothesis Testing using D_LR Metric

Arabpour, Alireza; Mozafari, Mahdieh

doi:10.22103/jmmrc.2013.1398

Linear Hypothesis Testing using D_LR Metric

Document Type : Research Paper

Authors

Alireza Arabpour ¹

Mahdieh Mozafari ²

¹ Department of Statistics, Shahid Bahonar University of Kerman, Kerman, Iran

² Department of Statistics, Higher Education Complex of Bam, Kerman, Iran

10.22103/jmmrc.2013.1398

Abstract

Several practical problems of hypotheses testing can be under a general linear model analysis of variance which would be examined. In analysis of variance, when the response random variable Y , has linear relationship with several random variables x, another important model as analysis of covariance can be used.
In this paper, assuming that Y is fuzzy and using D_LR metric, a method for testing the linear hypothesis has been proposed based on fuzzy techniques. In fact, in this method a set of confidence intervals has been used for creating fuzzy test statistic and fuzzy critical values. In addition, the proposed method has been mentioned for the reforming of the hypothesis testing when there is an uncertaity in accepting or rejecting hypotheses. Finally, by presenting two examples this method is illustrated.

Keywords

Analysis of covariance

Buckley's method

Confidence interval

D_LR metric