[GRASS-user] Linear regression between 2 rasters (old and new)

[Moritz Lennert]

On 30/09/11 16:39, António Rocha wrote:
> I
>
> I have been using r.series to calculate a linear regression slope for an
> old and new raster map using r.series. But now I need to also obtain the
> error. It seems not to be possible to use r.series. Is this true? if
> yes, what alternative do I have?

If by error you mean the error in each pixel, you can use the slope and 
offset values r.series gives you in r.mapcalc to calculate the 
theoretical value based on the linear equation and then again r.mapcalc 
to calculate the difference between the theoretical and the actual value.

Also check out r.regression.line.

Moritz