| Re: Definition of skewness [message #45107] |
Fri, 12 August 2005 13:41 |
JD Smith
Messages: 850
Registered: December 1999
|
Senior Member |
|
|
On Fri, 12 Aug 2005 16:30:33 +0000, Mike Chinander wrote:
> In article <MPG.1d66754d527d4ad6989a3d@news.frii.com>,
> David Fanning <davidf@dfanning.com> wrote:
>
>> No excuse!? Goodness, I could think of several, just off
>> the top of my head. Starting with the fact no one has gone
>> to the trouble to point it out to them. I really doubt that
>> RSI is so perverse as to *deliberately* leave inaccurate
>> information in its documentation just to see new users
>> squirm.
>>
>
> I wasn't implying that the inaccurate description was deliberate on RSI's part.
I find the documentation group at RSI to be very responsive (if a bit
understaffed). Send it in, and I'd wager good wampum it will get
fixed in the next release. Interestingly, none other than Richard
Stallman has found spelling errors in their docs (via the IDLWAVE help
files), which, of course, they fixed.
JD
|
|
|
|
| Re: Definition of skewness [message #45109 is a reply to message #45107] |
Fri, 12 August 2005 09:30  |
mchinand
Messages: 66
Registered: September 1996
|
Member |
|
|
In article <MPG.1d66754d527d4ad6989a3d@news.frii.com>,
David Fanning <davidf@dfanning.com> wrote:
> No excuse!? Goodness, I could think of several, just off
> the top of my head. Starting with the fact no one has gone
> to the trouble to point it out to them. I really doubt that
> RSI is so perverse as to *deliberately* leave inaccurate
> information in its documentation just to see new users
> squirm.
>
I wasn't implying that the inaccurate description was deliberate on RSI's part.
|
|
|
|
| Re: Definition of skewness [message #45110 is a reply to message #45109] |
Fri, 12 August 2005 08:59 |
David Fanning
Messages: 11724
Registered: August 2001
|
Senior Member |
|
|
Mike Chinander writes:
> While the SKEWNESS page does have the incorrect description, it does at least mention that
> it calls the MOMENT function and its help page does give the mathematical expression for
> skewness (3rd moment about mean as Ken stated above). That's still no excuse for having the
> wrong description of skewness, however.
No excuse!? Goodness, I could think of several, just off
the top of my head. Starting with the fact no one has gone
to the trouble to point it out to them. I really doubt that
RSI is so perverse as to *deliberately* leave inaccurate
information in its documentation just to see new users
squirm.
Cheers,
David
--
David Fanning, Ph.D.
Fanning Software Consulting, Inc.
Coyote's Guide to IDL Programming: http://www.dfanning.com/
|
|
|
|
| Re: Definition of skewness [message #45111 is a reply to message #45110] |
Fri, 12 August 2005 08:52 |
mchinand
Messages: 66
Registered: September 1996
|
Member |
|
|
In article <k-bowman-6A23C8.09010712082005@news.tamu.edu>,
Kenneth Bowman <k-bowman@null.tamu.edu> wrote:
>
> The documentation is incorrect. Skewness is related to the third moment about
> the mean.
>
> It would be extremely helpful if the IDL manuals included the mathematical
> expressions for quantities such as this, but unless they receive many requests,
> RSI is unlikely to update the docs.
>
While the SKEWNESS page does have the incorrect description, it does at least mention that
it calls the MOMENT function and its help page does give the mathematical expression for
skewness (3rd moment about mean as Ken stated above). That's still no excuse for having the
wrong description of skewness, however.
--Mike
--
Michael Chinander
m-chinander@uchicago.edu
Department of Radiology
University of Chicago
|
|
|
|
| Re: Definition of skewness [message #45112 is a reply to message #45111] |
Fri, 12 August 2005 07:01 |
K. Bowman
Messages: 330
Registered: May 2000
|
Senior Member |
|
|
In article <1123799104.723233.99170@f14g2000cwb.googlegroups.com>,
"envi35@yahoo.ca" <envi35@yahoo.ca> wrote:
> Hi there,
> I want to use the skewness of some data series to do a rough
> classification. But I'm confused with the IDL online help about the
> SKEWNESS function: Skewness determines whether a distribution is
> symmetric about its MAXIMUM. While in Microsoft Excel, it says Skewness
> is a characterization of the degree of asymmetry of a distribution
> around its MEAN.
> It seems that the MEAN is right according to the algorithm of the
> skewness function in IDL, why the online help of IDL says MAXIMUM? Is
> this a typo or else? Could anybody knows more about statistics give me
> some help?
>
> Thanks, Jenny
The documentation is incorrect. Skewness is related to the third moment about
the mean.
It would be extremely helpful if the IDL manuals included the mathematical
expressions for quantities such as this, but unless they receive many requests,
RSI is unlikely to update the docs.
Regards, Ken Bowman
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
