Dear all,
I'm using predict.gam (mgcv package) to predict count data (y) from line
transect to a regular grid. My model have this form:
y=offset(log(x1*0.6))+s(x2)+s(x3)+s(x4), family=quasipoisson,...
the offset is the area covered by a portion of a transect line
(length(x1)*observation distance(0.6)). The length is almost always 1 km
since I splitted the transect in 1 km segments. I have different length
value only for the segments at the end of the transects. The observation
distance is always the same.
To predict on a regular grid (2 km * 2 km), using predict.gam, should I use
the area of each cell or use 1 km for the offset variable x1? I obtained
more logical result with x1=1 km in my prediction grid.
Thanks
Samuel
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
