On Jun 18, 2009, at 5:01 AM, alessia matano wrote:
Dear all,
I 'm implementing the koenker procedure for quantile fixed effects.
Who he? Wuz 'dat?
I would like also to apply weights to the procedure, so that to give
more weight to the observation that better represent my original
sample (much larger than it is possible to use in R).
This contradicts the principle of the much beloved fortune("This is R")
Do you know if it is possible?
This contradicts the previous assertion.
How could I solve this problem?
For positive weights, you can multiply y and X by them, but don't
neglect the intercept, it deserves weight two [sic]. For negative
weights
you are asking for trouble.
Thank you
alessia
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
