I have a multivariate data set, and want to
see the effect of truncating the data at
different points based on phenotype (ie chuck
out the extreme so-many percent, I have the
percentiles from elsewhere). I would like to
do this within ASREML in order to save
setting up the data multiple times.
I don't want to lose the whole record for an
animal, so would like to be able to do
if( x > x_cutoff ) x = missing
as different animals may be extreme for
Is there a way of doing this?
I can see how using !filter I can take out whole
records, but I can't see how to zap specific
extreme values within a record.