Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Steve Samuels <sjsamuels@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Standard Errors for Skewness & Kurtosis |

Date |
Fri, 10 Sep 2010 18:09:49 -0400 |

The exact standard deviations (and hence, standard errors) for any distribution, not just the Gaussian, can be found in either edition of CR Rao, Linear Statistical Inference and its Applications, Wiley. However I suggest that you get the standard errors via jackknife or bootstrap. Steve Steven J. Samuels sjsamuels@gmail.com 18 Cantine's Island Saugerties NY 12477 USA Voice: 845-246-0774 Fax: 206-202-4783 On Fri, Sep 10, 2010 at 9:52 AM, Stas Kolenikov <skolenik@gmail.com> wrote: > Check the code; it must compute the standard errors somehow, although > it might do so under the assumption of normality. At any rate, the > standard error for kurtosis will be a function of the eighth moment of > the data, and that's a lot to ask: it may not exist, and even if it > does, it will be quite unstable unless you have a few thousand > observations. > > If Stata had contour plots, you could've constructed a cute empirical > likelihood diagram for the joint confidence set of skewness and > kurtosis (I've got the basic empirical likelihood code, but I've no > clue as to how to proceed with contour plots; I know Sergiy Radyakin > did some of them, but I am not sure mere mortals can reproduce his > work in Stata graphics :)). I think you can do this in R, I vaguely > remember doing this myself. > > On Thu, Sep 9, 2010 at 10:19 PM, Philip Burgess > <philip.burgess.uq@gmail.com> wrote: >> Stas; >> >> No - I've checked the Saved Results for sktest with no joy. >> >> Thanks; >> >> Philip >> >> On Fri, Sep 10, 2010 at 1:08 PM, Stas Kolenikov <skolenik@gmail.com> wrote: >>> On Thu, Sep 9, 2010 at 9:52 PM, Philip Burgess >>> <philip.burgess.uq@gmail.com> wrote: >>>> I can't find any ado that calculates the standard errors for skewness >>>> >>>> Do you know of such or how I might estimate these? >>> >>> Is there anything available as a by-product of -sktest-? If not, the >>> ado-file must compute the standard errors to perform the test, I >>> believe. >>> >>> -- >>> Stas Kolenikov, also found at http://stas.kolenikov.name >>> Small print: I use this email account for mailing lists only. >>> * >>> * For searches and help try: >>> * http://www.stata.com/help.cgi?search >>> * http://www.stata.com/support/statalist/faq >>> * http://www.ats.ucla.edu/stat/stata/ >>> >> >> * >> * For searches and help try: >> * http://www.stata.com/help.cgi?search >> * http://www.stata.com/support/statalist/faq >> * http://www.ats.ucla.edu/stat/stata/ >> > > > > -- > Stas Kolenikov, also found at http://stas.kolenikov.name > Small print: I use this email account for mailing lists only. > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:**Re: st: Standard Errors for Skewness & Kurtosis***From:*Steve Samuels <sjsamuels@gmail.com>

**References**:**st: Standard Errors for Skewness & Kurtosis***From:*Philip Burgess <philip.burgess.uq@gmail.com>

**Re: st: Standard Errors for Skewness & Kurtosis***From:*Stas Kolenikov <skolenik@gmail.com>

**Re: st: Standard Errors for Skewness & Kurtosis***From:*Philip Burgess <philip.burgess.uq@gmail.com>

**Re: st: Standard Errors for Skewness & Kurtosis***From:*Stas Kolenikov <skolenik@gmail.com>

- Prev by Date:
**st: Subsetting a -return- matrix in a single step** - Next by Date:
**st: RE: Identifying influential observations after svy: logit command** - Previous by thread:
**Re: st: Standard Errors for Skewness & Kurtosis** - Next by thread:
**Re: st: Standard Errors for Skewness & Kurtosis** - Index(es):