Skip to main content
Article
On Polynomial Transformations For Simulating Multivariate Non-normal Distributions
Publications
  • Todd C. Headrick, Southern Illinois University Carbondale
Comments

Published in the Journal of Modern Applied Statistical Methods, 2004, Vol. 3, No. 1, pp.65-71.

Publication Date
4-1-2004
Abstract

Procedures are introduced and discussed for increasing the computational and statistical efficiency of polynomial transformations used in Monte Carlo or simulation studies. Comparisons are also made between polynomials of order three and five in terms of (a) computational and statistical efficiency, (b) the skew and kurtosis boundary, and (c) boundaries for Pearson correlations. It is also shown how ranked data can be simulated for specified Spearman correlations and sample sizes. Potential consequences of nonmonotonic transformations on rank correlations are also discussed.

, Monte Carlo methods, polynomial transformations, nonnormality

Citation Information
Todd C. Headrick. "On Polynomial Transformations For Simulating Multivariate Non-normal Distributions" (2004)
Available at: http://works.bepress.com/todd_headrick/21/