You shouldn't use use r-squared in the context of glm, in fact it's not possible. But if you need try calculating pseudo r-squared values ________________________________ From: R-help <[email protected]> on behalf of Rolf Turner <[email protected]> Sent: Saturday, September 17, 2022 12:29:56 AM To: Kayla Bazzana <[email protected]> Cc: [email protected] <[email protected]> Subject: Re: [R] nlme gls issue
On Fri, 16 Sep 2022 13:48:55 +0000 Kayla Bazzana <[email protected]> wrote: > Hi there, > > I'm having issues running a gls within the nlme package that neither > I nor any of my colleagues can figure out. The gls itself seems to > run fine (i.e. doesn't give an error message and produces a seemingly > normal summary output), but when I try to calculate the rsquared of > the gls model, it simply returns an "NA". Is this an issue you've > encountered before? If so, can you point me in the right direction of > how to remedy it? I believe that fortunes::fortune(254), although not directly applicable, might be relevant. :-) If you *really* believe that r-squared makes some kind of sense in the context of *generalised* least squares, you should probably direct further enquires to r-sig-mixed-models. cheers, Rolf Turner -- Honorary Research Fellow Department of Statistics University of Auckland Phone: +64-9-373-7599 ext. 88276 ______________________________________________ [email protected] mailing list -- To UNSUBSCRIBE and more, see 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. [[alternative HTML version deleted]] ______________________________________________ [email protected] mailing list -- To UNSUBSCRIBE and more, see 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.
