Dear all, just to confirm that as far as I know (Yves please correct me if I'm wrong) Achim's fix is currently the way to go.
The sum-of-squares statistics part of 'plm' outputs is currently quite minimal and due for some extension. Cases like Eduardo's give us a sample of what the useRs may need, so thanks for the feedback. And of course thanks to Achim for the prompt help. Cheers Giovanni -----Original Message----- From: Achim Zeileis [mailto:achim.zeil...@uibk.ac.at] Sent: Thu 08/04/2010 21.21 To: ECAMF Cc: r-help@r-project.org; yves.croiss...@univ-reunion.fr; Millo Giovanni Subject: Re: [R] Accessing elements of plm outputs On Thu, 8 Apr 2010, ECAMF wrote: > > Dear all, > > I've just migrated from STATA to R for runing panel regressions and I was > very happy to discover the plm package. However, I have a problem when > trying to access the "Total Sum of Squares" and "Residual Sum of Squares" on > this output: > >> summary(output) > > Oneway (individual) effect Within Model > > Call: > plm(formula = Y ~ X1 + X2, data = db, model = "within") > > Unbalanced Panel: n=10, T=9-11, N=108 > > Residuals : > Min. 1st Qu. Median 3rd Qu. Max. > -6.500 -2.200 -0.374 1.550 8.730 > > Coefficients : > Estimate Std. Error t-value Pr(>|t|) > X1 113.302650 8.517736 13.302 <2e-16 *** > X2 -0.084414 0.109625 -0.770 0.4432 > --- > Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 > > Total Sum of Squares: 3208.3 > Residual Sum of Squares: 1059.6 > F-statistic: 97.3365 on 2 and 96 DF, p-value: < 2.22e-16 > > > I would like to do so because I'm running some hundreds times a similar > regression and I want to store those results in a vector and then plot them. > I've tried to do so with > >> summary(output)[] > > but neither the "Total Sum of Squares" or the "Residual Sum of Squares" are > on the list. The residual sum of squares can be computed via sum(residuals(output)^2) The total sum of squares is more difficult, I think. plm contains a tss() generic with suitable methods - but this is only used internally but not exported in the user interface. Thus, you currently have to do plm:::tss.plm(output) This is really dirty as it accesses a specific method (rather than the generic) in the namespace (rather than the exported user interface). But I don't think there's currently a better way. The package authors (both Cc) might be able to give more guidance though. hth, Z > I would be glad if somebody can help me. > > Thank you very much! > > Eduardo Marinho. > -- > View this message in context: > http://n4.nabble.com/Accessing-elements-of-plm-outputs-tp1774143p1774143.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > 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. Ai sensi del D.Lgs. 196/2003 si precisa che le informazi...{{dropped:15}} ______________________________________________ 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.
