|
EconStor >
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) >
Lehrstuhl für Statistik und Ökonometrie, Universität Erlangen-Nürnberg >
Diskussionspapiere des Lehrstuhls für Statistik und Ökonometrie, FAU Erlangen-Nürnberg >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10419/29570
|
| | |
| Title: | | A note on the construction of generalized Tukey-type transformations  |
| Authors: | | Fischer, Matthias J. |
| Issue Date: | | 2006 |
| Series/Report no.: | | Diskussionspapiere // Friedrich-Alexander-Universität Erlangen-Nürnberg, Lehrstuhl für Statistik und Ökonometrie 73/2006 |
| Abstract: | | One possibility to construct heavy tail distributions is to directly manipulate a standard Gaussian random variable by means of transformations which satisfy certain conditions. This approach dates back to Tukey (1960) who introduces the popular H-transformation. Alternatively, the K-transformation of MacGillivray & Cannon (1997) or the J-transformation of Fischer & Klein (2004) may be used. Recently, Klein & Fischer (2006) proposed a very general power kurtosis transformation which includes the above-mentioned transformations as special cases. Unfortunately, their transformation requires an infinite number of unknown parameters to be estimated. In contrast, we introduce a very simple method to construct êexible kurtosis transformations. In particular, manageable superstructures are suggested in order to statistically discriminate between H-, J-and K-distributions (associated to H-, J- and K-transformations). |
| Subjects: | | Generalized kurtosis transformation H-transformation |
| Document Type: | | Working Paper |
| Appears in Collections: | | Diskussionspapiere des Lehrstuhls für Statistik und Ökonometrie, FAU Erlangen-Nürnberg
|
| Files in This Item:
| |
|
| No. of Downloads:
| |
| last Month |
last 3 Month |
total |
|
|
|
|
|
| |
| | |
Download bibliographical data as:
BibTeX
|
| |
Share on:http://hdl.handle.net/10419/29570
|
Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.
|