Parameter Estimation of Exponentiated U-Quadratic Distribution: Alternative Maximum Likelihood and Percentile Methods
Mustapha Muhammad *
Department of Mathematical Sciences, Bayero University Kano (BUK), Nigeria.
Sadiya Ali Rano
Department of Mathematical Sciences, Bayero University Kano (BUK), Nigeria.
Ruqayya Ibrahim Sani
Department of Mathematical Sciences, Bayero University Kano (BUK), Nigeria.
Murtala Maitama Ahmad
Department of Mathematics and Statistics, Federal Polytechnic Kaura Namoda, Zamfara, Nigeria.
Abba Sani Sulaiman
Department of Mathematical Sciences, Bayero University Kano (BUK), Nigeria.
*Author to whom correspondence should be addressed.
Abstract
In this article, exponentiated U-quadratic distribution (EUq) is proposed by exponentiation procedure. The quantile function and rth moment of the new model are computed. Estimation of parameter by the alternative maximum likelihood and estimation based on percentiles are established and compare their performances through numerical simulations. The results show that both methods are suitable for the parameter estimation of EUq distribution. A real data set is used to compare the fit of the two proposed estimation method using Kolmogorov Smirnov test (KS).
Keywords: U-qadrtic distribution, maximum likelihood estimation, estimation by percentile.