Goodness of fit tests for Nakagami distribution based on smooth tests


ÖZONUR D., GÖKPINAR F., GÖKPINAR E., BAYRAK H.

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, vol.45, no.7, pp.1876-1886, 2016 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 45 Issue: 7
  • Publication Date: 2016
  • Doi Number: 10.1080/03610926.2013.867998
  • Journal Name: COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1876-1886
  • Keywords: Nakagami distribution, smooth tests, goodness of fit, Type-I error, power of test, 62G10, 62F40
  • Gazi University Affiliated: Yes

Abstract

Nakagami distribution is one of the most common distributions used to model positive valued and right skewed data. In this study, we interest goodness of fit problem for Nakagami distribution. Thus, we propose smooth tests for Nakagami distribution based on orthonormal functions. We also compare these tests with some classical goodness of fit tests such as Cramer-von Mises, Anderson-Darling, and Kolmogorov-Smirnov tests in respect to type-I error rates and powers of tests. Simulation study indicates that smooth tests give better results than these classical tests give in respect to almost all cases considered.