mgcv package performs a linear extrapolation when the
newdat argument of the
predict function contains values outside the range of the training covariates. I am unable to find out what happens in this use case for the
gamboostLSS package and the
mboost packages on which it is based.
Just to close this issue an to let others know [I wasn't aware of this open question]:
We had an email exchange in 2015 and decided to use linear extrapolation for smooth effects (both, P-splines and constraint P-splines). This was implemented in mboost 2.5-0. See
news(Version >= "2.5-0", package = "mboost") and
package?mboost for more details.