Abstract
Abstract
In parameter estimation techniques, there are several methods for estimating the distribution parameters in life data analysis. However, most of them are less efficient than Bayes’ method based on the informative prior. Thus, the main objective of this study is to present an optimal numerical technique, Picard’s method, for estimating Burr type-XII distribution parameters and compare them with Bayes’ method based on the informative gamma and kernel priors. A comparison between these estimators is provided using an extensive Monte Carlo simulation. The simulation results indicated that Picard’s method is highly favorable, which provides better estimates and outperforms Bayes’ method based on the generalized progressive hybrid censoring scheme. Finally, two real dataset analyses are presented to illustrate the efficiency of the proposed methods.
Publisher
Research Square Platform LLC
Reference31 articles.
1. Kernel Inference on the Generalized Gamma Distribution based on Generalized Order Statistics;Ahsanullah M;Journal of Statistical Theory and Applications,2013
2. Testing Parameters of a Gamma Distribution for Small Samples;Bhaumik DK;Technimetrics,2009
3. "On a general system of distributions III. The sample range";Burr Irving W;Journal of the American Statistical Association,1968
4. On a general system of distributions. I. Its curve- shaped characteristics. II. The sample median";Burr Irving W;Journal of the American Statistical Association,1968
5. An estimation of the entropy for a Rayleigh distribution based on doubly generalized Type-II hybrid censored samples;Cho Y;Entropy,2014