The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case

Details The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case

2010-10-11

arxiv.org/abs/1010.2265v4

Mathematics

Statistics Theory

40 pages; 4 tables; 9 figures. Keywords: Gaussianizing, family of heavy-tailed distributions, Tukey's $h$ distribution, Lamber

Scientific paper

I use a parametric, bijective transformation to generate heavy tail versions Y of an arbitrary random variable (RV) X ~ F_X, by similar concepts as in Goerg (2011) for skewed RVs. The tail behavior of the so-called heavy tail Lambert W x F_X RV Y depends on a tail parameter delta >= 0; for delta = 0, Y = X, for delta > 0 Y has heavier tails than X. For X being Gaussian, this meta-family of heavy-tailed distributions reduces to Tukey's h distribution. Lambert's W function provides an explicit inverse transformation, which can be used to remove skewness and heavy tails from data and then apply standard methods and models to this so obtained "nice" (Gaussianized) data. The optimal inverse transformation can be estimated by maximum likelihood. This transformation based approach to heavy tails also yields analytical, concise and simple expressions for the cumulative distribution (cdf) G_Y(y) and probability density function (pdf) g_Y(y). As a special case, I present explicit expressions for Tukey's h pdf and cdf - to the authors knowledge for the first time in the literature. Applications to a simulated Cauchy sample, S&P 500 log-returns, as well as solar flares data demonstrate the usefulness of the introduced methodology. The R package "LambertW" (cran.r-project.org/web/packages/LambertW) contains a wide range of methods presented here and is publicly available at CRAN

Affiliated with

Also associated with

No associations

Rating

The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Lambert Way to Gaussianize skewed, heavy tailed data with the inverse of Tukey's h transformation as a special case will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-607383