OASIS Mailing List ArchivesView the OASIS mailing list archive below
or browse/search using MarkMail.

 


Help: OASIS Mailing Lists Help | MarkMail Help

office-formula message

[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]


Subject: Re: [office-formula] OFFICE-1185 LINEST


On Tue, 2010-04-27 at 06:56 -0600, Eike Rathke wrote:
> Hi Andreas,
> 
> On Monday, 2010-04-26 12:29:12 -0600, Andreas J. Guelzow wrote:
> 
> > What does "number of variables of the regression
> > analysis including the intercept" mean? 
> > 
> > The intercept is not a variable. It doesn't seem likely that the degrees
> > of freedom are independent from whether the intercept is forced to be
> > zero or not but the same formulation is used in both cases.
> 
> If the intercept is forced to 0 it isn't a variable.
> 
> I propose to remove "including the intercept" from both formulas and:
> 
> For Const=TRUE() change to df=n-k-1
> 
> For Const=FALSE() change to df=n-k
> 
> In both cases n is the number of data points and k is the number of
> columns of knownX.
> 
> Does that sound more likely?

That is what I would expect.

Thanks

Andreas



[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]