Re: [R] Significance of degrees of freedom in nlme

From: Spencer Graves <spencer.graves_at_pdf.com>
Date: Wed 08 Feb 2006 - 05:01:30 EST

          Your question begins, "Dear Dr. Bates", yet Bates does not appear as an addressee in the copy of your question that I recieved via r-help. I will offer a couple of suggestions in the hopes that they might help you. Since your question did not include enough detail for anyone to answer without additional information, I used 'RSiteSearch("gabriela escati peñaloza")' to find earlier posts that might be related. This generated 14 hits, the most relevant of which seemed to be "http://finzi.psych.upenn.edu/R/Rhelp02a/archive/69466.html". From this, I copy the following:

formula(my data.gd)
dLt ~ Lt | ID
TasavB<- function(Lt, Linf, K) (K*(Linf-Lt)) my model.nlme <- nlme (dLt ~ TasavB(Lt, Linf, K), data = my data.gd,
fixed = list(Linf ~ 1, K ~ 1),
start = list(fixed = c(70, 0.4)),
na.action= na.include, naPattern = ~!is.na(dLt))

          I assume something got garbled here, because constructs like "my data.gd" generate a 'syntax error' for me; I therefore assume it is "my_data.gd" (with an underscore between "my" and "data.gd".) Try the following:

sapply(my_data.gd, class)

          What columns of my_data.gd are factors, and how do they relate to Linf and K? You can explore this using "table".

          If you would like more help from this listserve, please submit another post. Before you do, however, PLEASE do read the posting guide! "www.R-project.org/posting-guide.html", and try some of the things suggested there. In particular, if you haven't already, try RSiteSearch for "nlme degrees of freedom" and anything else that seems relevant to you. Also, before your next post, I encourage you to try to develop the simplest, self-contained example that illustrates your question. I believe you will more likely receive faster, more useful replies if you make it easier for people to help you.

	  hope this helps,
	  spencer graves

gabriela escati peñaloza wrote:

> Dear Dr. Bates,
> Thank you very much for your response. I had consulted
> the algorithm described in Pinheiro and Bates.
> However, what I don't understand (among other things)
> is why my two parameters appear to be estimated at
> different grouping levels (based on the DF values).
> Affect this different values of DF at the estimates
> parameters? The estimates fixed effects were get at
> the same level of grouping?
> I apreciate any response.
>
>
>
>
> Lic. Gabriela Escati Peñaloza
> Biología y Manejo de Recursos Acuáticos
> Centro Nacional Patagónico(CENPAT).
> CONICET
> Bvd. Brown s/nº.
> (U9120ACV)Pto. Madryn
> Chubut
> Argentina
>
> Tel: 54-2965/451301/451024/451375/45401 (Int:277)
> Fax: 54-29657451543
>
>
>
>
>
>
>
> ___________________________________________________________
> 1GB gratis, Antivirus y Antispam
> Correo Yahoo!, el mejor correo web del mundo
> http://correo.yahoo.com.ar
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Wed Feb 08 05:20:30 2006

This archive was generated by hypermail 2.1.8 : Wed 08 Feb 2006 - 23:29:28 EST