Dear Arne, the inclusion of weights in the (mainly-GLS-related-) procedures in 'plm' is not obvious: at least, it is not to me. Maybe you might apply the weights to the data before using them in estimation, which I have done in the past, although it was then meant to reflect stratification, not attrition: I admit my utter ignorance on this last particular subject.
Unless you can resort to some pre-treatment of the data, you might be better served with nlme/lme4. Should you need a quick "translation" of syntax from 'plm' towards 'nlme', you van find it here, section 7: http://www.jstatsoft.org/v27/i02 Best wishes, Giovanni ---------- Original message -------------------- Message: 145 Date: Thu, 10 Feb 2011 01:51:33 -0800 (PST) From: Arne <arne.war...@googlemail.com> To: r-help@r-project.org Subject: [R] Longitudinal Weights in PLM package Message-ID: <1297331493488-3298823.p...@n4.nabble.com> Content-Type: text/plain; charset=UTF-8 Hi all, I a semi-beginner with R and I am working with the plm package to examine a longitudinal dataset. Each individual in this dataset has a longitudinal weight for the probability that he or she remains in the sample. Unfortunately, I have not found an argument to use weights in the plm function? I tried ?weights=? like in standard lm or in nlme or lm4 but it does not work. I asked the maintainer but I have not received a reply yet. Therefore, I would like to ask you whether I can use plm with longitudinal weights or if I have to switch to other packages dealing with longitudinal data? Thank you in advance! Best regards, Arne ----------- End original message --------------------- Giovanni Millo Research Dept., Assicurazioni Generali SpA Via Machiavelli 4, 34132 Trieste (Italy) tel. +39 040 671184 fax +39 040 671160 Ai sensi del D.Lgs. 196/2003 si precisa che le informazi...{{dropped:13}} ______________________________________________ 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.