There has been much discussion on the validity of MS Excel statistical functions.
MS has been beat up pretty badly over it.
MS even admits their R2 chart calculations are incorrect ...
http://support.microsoft.com/kb/829249
"You will receive an incorrect R-squared value in the chart tool in Excel 2003"

Here are a couple of papers that discuss some Excel statistical issues...
http://www.daheiser.info/excel/frontpage.html
http://en.wikibooks.org/wiki/Statist...erics_in_Excel
--
Jim Cone
San Francisco, USA
http://www.realezsites.com/bus/primitivesoftware
(Excel Add-ins / Excel Programming)



"Bjoern"
wrote in message
Excel computes the R-squared of an exponential regression wrongly: instead of
thecorrect result it reports the R-squared of the underlying linera
regression of the logarithm of the data. The two numbers are close if the
correlation is good, put far apart if it isn't. This Excel grossly
exaggerates the R-squared.

I am trying to bring this to the attention of Microsoft. It is of some
importance to me as I will be teaching this topic to my Math class in two
weeks.

So far I have not been able to wade through the layers of bureaucracy.
--
Bjoern Schellenberg

----------------
This post is a suggestion for Microsoft, and Microsoft responds to the
suggestions with the most votes. To vote for this suggestion, click the "I
Agree" button in the message pane. If you do not see the button, follow this
link to open the suggestion in the Microsoft Web-based Newsreader and then
click "I Agree" in the message pane.

http://www.microsoft.com/office/comm...lic.excel.misc