Date:         Tue, 23 Nov 1999 10:45:15 +0000
Reply-To:     "R. Allan Reese" <R.A.Reese@GRI.HULL.AC.UK>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "R. Allan Reese" <R.A.Reese@GRI.HULL.AC.UK>
Subject:      Re: skew statistics re-scaled?
Comments: To: "Nichols, David" <nichols@SPSS.COM>
In-Reply-To:  <4E1F1ECF4049D3118C9900A024CDCB6456AEC3@hermes.spss.com>
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Mon, 22 Nov 1999, Nichols, David wrote:

> Both skewness and kurtosis would be 0 for a perfectly normal distribution.

Oh no it isn't! (Yes, it's that time of year.)

I'll let everyone check what the kurtosis of an N(0,1) distribution might
be, with the comment that Kendall and Buckland state "It is doubtful
whether any single ratio can adequately measure the quality of
peakedness" and the observation that in nearly thirty years I have never
quoted or used the kurtosis value in an analysis.

R. Allan Reese                       Email: r.a.reese@gri.hull.ac.uk
Associate Manager                    Direct voice:   +44 1482 466845
Graduate Research Institute          Voice messages: +44 1482 466844
Hull University, Hull HU6 7RX, UK.   Fax:            +44 1482 466846
====================================================================
Hull Univ - moving up in the First Division.  Daily Telegraph 4/8/99