Simulating Burr Type VII Distributions through the Method of ??-moments and ??-correlations

• Published in: Journal of Statistical and Econometric Methods Vol. 3; no. 3
• Main Authors: Pant, Mohan D, Headrick, Todd C
• Format: Journal Article
• Language: English
• Published: Christchurch Scientific Press International Limited 01.01.2014
• Subjects: Monte Carlo simulation
• ISSN: 2241-0384

Burr Type VII, a one-parameter non-normal distribution, is among the less studied distributions, especially, in the contexts of statistical modeling and simulation studies. The main purpose of this study is to introduce a methodology for simulating univariate and multivariate Burr Type VII distributions through the method of ??-moments and ??-correlations. The methodology can be applied in statistical modeling of events in a variety of applied mathematical contexts and Monte Carlo simulation studies. Numerical examples are provided to demonstrate that ??-moment-based Burr Type VII distributions are superior to their conventional moment-based analogs in terms of distribution fitting and estimation. Simulation results presented in this study also demonstrate that the estimates of ??-skew, ??-kurtosis, and ??-correlation are substantially superior to their conventional product-moment based counterparts of skew, kurtosis, and Pearson correlation in terms of relative bias and relative efficiency when distributions with greater departure from normality are used.