Hello All,

I am trying to estimate a generalized linear model using a single dummy
variable (bilat). I want to use contr.sum, in which (please correct me if I
am wrong) the implicit coefficient on the contrast equals the negative of
the sum of all estimated coefficients.

I cannot get the contrast to work correctly. The implicit coefficient is
way to large (I checked this using the desmat - option dev - package in
Stata). I do:

contrasts(bilat) <- contr.sum(levels(bilat))
mod_1 <- gamlss(d ~ bilat, family=BEINF, data=df)

but this problem is not specific to gamlss. The same problem occurs also,
e.g. in
contrasts(bilat) <- contr.sum(levels(bilat))
mod_2 <- lm(d ~ bilat, data=df)

What am I doing wrong? Thank you for help!

Serguei

________________________________________
Austrian Institute of Economic Research (WIFO)

P.O.Box 91                          Tel.: +43-1-7982601-231
1103 Vienna, Austria        Fax: +43-1-7989386

Mail: serguei.kaniov...@wifo.ac.at
http://www.wifo.ac.at/Serguei.Kaniovski
        [[alternative HTML version deleted]]

______________________________________________
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.

Reply via email to