Comparison between Bayesian and Maximum Likelihood Methods for parameters and the Reliability function of Perks Distribution

  • Shurooq A. Al-Sultany Department of Mathematics, College of Science, Al-Mustansiriyah University, Baghdad, Iraq.
  • Sahar A. Mohammed Department of Mathematics, College of Science, Al-Mustansiriyah University, Baghdad, Iraq.

Abstract

In this paper, we have derived Bayesian estimation for the parameters and reliability function of Perks distribution based on two different loss functions, Lindley’s approximation has been used to obtain those values. It is assumed that the parameter behaves as a random variable have a Gumbell Type P prior with non-informative is used. And after the derivation of mathematical formulas of those estimations, the simulation method was used for comparison depending on mean square error (MSE) values and integrated mean absolute percentage error (IMAPE) values respectively. Among of conclusion that have been reached, it is observed that, the LE-NR estimate introduced the best perform for estimating the parameter λ.

Published
Mar 4, 2018
How to Cite
AL-SULTANY, Shurooq A.; MOHAMMED, Sahar A.. Comparison between Bayesian and Maximum Likelihood Methods for parameters and the Reliability function of Perks Distribution. Iraqi Journal of Science, [S.l.], p. 369-376, mar. 2018. ISSN 2312-1637. Available at: <http://scbaghdad.edu.iq/eijs/index.php/eijs/article/view/179>. Date accessed: 22 june 2018.
Section
Mathematics