Stat Papers (2010) 51:209–226
DOI 10.1007/s00362-008-0133-4
REGULAR ARTICLE
Fuzzy p-value in testing fuzzy hypotheses
with crisp data
Abbas Parchami · S. Mahmoud Taheri ·
Mashaallah Mashinchi
Received: 11 April 2007 / Accepted: 5 March 2008 / Published online: 22 April 2008
© Springer-Verlag 2008
Abstract In testing statistical hypotheses, as in other statistical problems, we may be
confronted with fuzzy concepts. This paper deals with the problem of testing hypothe-
ses, when the hypotheses are fuzzy and the data are crisp. We first introduce the notion
of fuzzy p-value, by applying the extension principle and then present an approach
for testing fuzzy hypotheses by comparing a fuzzy p-value and a fuzzy significance
level, based on a comparison of two fuzzy sets. Numerical examples are also provided
to illustrate the approach.
Keywords Testing hypotheses · Monotone likelihood ratio · Fuzzy hypothesis ·
Fuzzy p-value · Fuzzy significance level
1 Introduction and background
Statistical analysis, in traditional form, is based on the crispness of data, random vari-
ables, hypotheses, decision rules and parameters. In classical testing hypotheses the
hypotheses are crisp. For example, when we test the difference between two pop-
ulation means, the ordinary null hypothesis stipulates the difference between these
A. Parchami · M. Mashinchi
Department of Statistics, Faculty of Mathematics and Computer Sciences,
Shahid Bahonar University of Kerman, Kerman, Iran
S. M. Taheri (B )
Department of Mathematical Sciences,
Isfahan University of Technology (IUT), Isfahan 84156-83111, Iran
e-mail: taheri@cc.iut.ac.ir
S. M. Taheri
Statistical Research and Training Center (SRTC), Tehran, Iran
123