- September 9, 2020
- Posted by: RSIS Team
- Categories: IJRIAS, Statistics
International Journal of Research and Innovation in Social Science (IJRISS) | Volume V, Issue IV, April 2020 | ISSN 2454–6186
Extension of Comparative Analysis of Estimation Methods for Frechet Distribution Parameters
Koyejo S.O.1, Akomolafe A.A.1, Awogbemi C.A.2*, Oladimeji O.O.3
1Department of Statistics, Federal University of Technology, Akure, Nigeria
2Department of Statistics, National Mathematical Centre, Kwali, Abuja, Nigeria
3Department of Statistics, Osun State College of Science and Technology, Esa-Oke, Nigeria
*Corresponding Author
Abstract: – Parameter estimation is very significant for any probability distribution and therefore, various estimation methods are frequently studied in the statistical literature. This research examined six methods to estimate the parameters of Frechet distribution (Generalized Maximum Likelihood Estimator, Maximum Product Spacing Estimator, L-Moment Estimator and Method of Moment Estimator). These methods were compared using Bias, Mean Square Error, Mean Absolute Error and Variance criteria as applied to Nigeria Maximum Annual Rainfall (2010-2015). Simulation study was carried out with simulated data set at different sample sizes and different levels of the shape and scale parameters. The simulation study and analysis revealed that the Generalized Maximum Likelihood (GML) Estimation was the best estimation method in terms of the Mean square Error, Mean Absolute Error and Variance; while Maximum Product Spacing Estimation method was the best estimation method with real life data.
Keywords: Parameter Estimation, Generalized Maximum Likelihood Estimator, Maximum Product Spacing Estimator, L-Moment Estimator and Method of Moment Estimator
