Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/29597 
Authors: 
Year of Publication: 
2000
Series/Report no.: 
Diskussionspapier No. 36/2000
Publisher: 
Friedrich-Alexander-Universität Erlangen-Nürnburg, Lehrstuhl für Statistik und Ökonometrie, Nürnberg
Abstract: 
Tukey (1960) derived via the technique of transformation of variables starting from the normal distribution a family of skewed and leptokurtic distributions. Skewness and leptokurtosis are determined by two parametersg and h. Therefore, the family was called gh-distributions. We modify Tukeys proposal such that other symmetric distributions will be taken as starting point for the transformation of variables. We speak about a family gh transformed symmetrical distributions. Especially, we condiser the Laplace distribution and the t-distribution with a fixed number of degrees. The aim ist to show, what kind of distribution take place between a leptokurtic symmetric distribution and the parameter g and . Because of numerical problems with maximum likelihood. Hoaglins (1983) technique of estimation by quantiles it used. We demonstrate how the three families of gh-transformed symmetrical distributions work fpr real financial data sets that stem from a skewed and leptokurtic distribution.
Document Type: 
Working Paper

Files in This Item:
File
Size
385.15 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.