Re: Gnumeric regression is wrong?
- From: "Andreas J. Guelzow" <aguelzow math concordia ab ca>
- To: Morten Welinder <terra diku dk>
- Cc: reubendb goshen edu, gnumeric-list gnome org
- Subject: Re: Gnumeric regression is wrong?
- Date: Thu, 27 Sep 2001 17:36:33 -0600
There is definitely something wrong with the regression calculations in
the data analysis tools. It seems that the standrard error for the
parameter estimates are switched (and then all the calculations based on
them seem to be wrong).
I'll try to locate the exact problem.
Morten Welinder wrote:
Gnumeric's regression stuff is supposed to match Excel's, modulo
bugs (in either).
Please supply a concrete example of a regression that Gnumeric
does differently than Excel:
* The data.
* The result you get from Gnumeric.
* The result you get from Excel.
* The versions of Gnumeric and Excel you are using.
We're probably not too interested in bugs before, say, Gnumeric
version 0.64. Please check a newer version first.
Prof. Dr. Andreas J. Guelzow
Assoc. Prof of Mathematics
Concordia University College of Alberta
] [Thread Prev