Re: [ferret_users] R-square problem

[Ana Redondo <a.rodriguez@xxxxxxxxx>]

Title: Re: [ferret_users] R-square problem

Hi Ansley,

Yes the values of Rsquare are larger than 1:


yes? stat rsquare
 Total # of data points: 1512 (72*21*1*1)
 # flagged as bad  data: 0
 Minimum value: 0.34722
 Maximum value: 1.2
 Mean    value: 0.89056 (unweighted average)
 Standard deviation: 0.10312

Any ideas??

Thanks

Ana


On 20/10/09 2:16 AM, "Ansley Manke" <Ansley.B.Manke@xxxxxxxx> wrote:

> Hi Ana,
> Yes, the values of rsquare should be between 0 and 1.   If you look at the result of
>
>    yes? STAT rsquare
>
> are the values really larger than 1?  I wonder if the automatically chosen color fill levels in the FILL command are making the color bar extend higher than 1 even though the values of the data field are not actually larger than 1.
>
> Another possibility is that the accuracy of numeric calculations is putting values slightly larger than 1.  Here too the STAT command might tell us more.
>
> Ansley
>
>
> Ana Redondo wrote: 
> >  R-square problem Hi,
> >  
> > I am doing a linear regression between two independent variables in order to find out the R-square. This is how I am doing it:
> >   yes? Let P=var_1
> >   yes? Let Q=var_2
> >   yes? Go regresst
> >   yes? show var
> >   yes? fill rsquare
> >  
> > But when filling the R-square (and I also list some values to test) I realized that some values are greater than 1!!!!!!!!  Isn’t it R-square the coefficient of determination? If so it should be 0<R^2<1, what I am doing wrong???
> >  
> >  
> > Thanks
> >  
> > Ana