Far East Journal of Theoretical Statistics
© 2016 Pushpa Publishing House, Allahabad, India
Published Online: March 2016
http://dx.doi.org/10.17654/TS052010001
Volume 52, Number 1, 2016, Pages 1-15 ISSN: 0972-0863
Received: June 7, 2015; Revised: July 9, 2015; Accepted: July 25, 2015
2010 Mathematics Subject Classification: 62F10.
Keywords and phrases: beta function, digamma function, gamma function, inverse Weibull
distribution, method of maximum likelihood, method of product spacings, Newton-Raphson
method, trigamma function.
Communicated by Jinyu Li; Editor: Advances and Applications in Statistics: Published by
Pushpa Publishing House.
METHOD OF PRODUCT SPACINGS PARAMETER
ESTIMATION FOR BETA INVERSE
WEIBULL DISTRIBUTION
Mezbahur Rahman, Dayeong An and Mohammad Shaha Alam Patwary
Department of Mathematics and Statistics
Minnesota State University
Mankato, MN 56001, U. S. A.
e-mail: mezbahur.rahman@mnsu.edu
dayeong.an@mnsu.edu
mohammad-shaha.patwary@mnsu.edu
Abstract
The inverse Weibull distribution is one of the widely applied
distributions. In this paper, we are going to extend the study of
the beta inverse Weibull distribution (BIW). The BIW with three
parameters is analyzed by using the method of product spacing
(MPS) and compared with the maximum likelihood estimate (MLE).
To estimate the model parameters, Newton-Raphson method is applied
and the table of simulation results is shown. Finally, practical use
of the model is demonstrated by dint of an application to real data.
For the real data computation, the estimate of the variance-covariance
matrix and the estimates are provided.