Dynamic tracing results: a comparison between maximum likelihood and Bayesian techniques
Khaled Mohamed Khedher,Rizwan Munir,Muzamal Hussain,Rana Muhammad Akram Muntazir,Lahcen Azrar
Abstract
In present study, Pareto distribution is used to find the estimation of different sample size. The maximum likelihood method and Bayesian method are compared for best estimation. R Language is used for Bayesian method and maximum likelihood method that are presented in tabular form. The traceable results are presented that are extracted with the WinBUGS software. The estimated value decrease as the sample size increased. The gamma and lambda for the Bayesian method is the best estimation rather than the maximum likelihood method. The maximum likelihood method is less estimate as compared to the Bayesian method for closeness of the estimate. It is detected that the Bayesian method is the best one as it has the least standard error with few exceptions. The part of the data analyzed here comprises the total damage by 142 fires in Norway for the year 1975, for claims above 500,000 Norwegian Krones. The loses are recorded in 1000’s of Norwegian Krones.
Key Words
computations; dynamic trace; Pareto distribution; R Language; simulation
Address
Khaled Mohamed Khedher — Department of Civil Engineering, College of Engineering, King Khalid University, Abha, 61421, Saudi Arabia
Rizwan Munir — School of Statistics and Data Science, Jiangxi University of Finance and Economics, Nanchang 330013, China
Muzamal Hussain — Department of Physical and Numerical Sciences, University of Rasul, 50400, Mandi Bahaudin, Punjab, Pakistan
Rana Muhammad Akram Muntazir — Department of Mathematics, Lahore Leads University, Lahore
Lahcen Azrar — Department of Applied Mathematics and Informatics, ENSAM, Mohammed V University of Rabat, Morocco
PDF Viewer
Preview is limited to the first 3 pages. Sign in to access the full PDF.
