[R-sig-ME] spatial correlation structure for GLS (nlme)

ONKELINX, Thierry Thierry.ONKELINX at inbo.be
Fri Dec 10 13:18:45 CET 2010

Dear Augustin,

Which residuals did you use? You need to normalised residuals because they take the effect of the correlation function into account.

Best regards,


ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek
team Biometrie & Kwaliteitszorg
Gaverstraat 4
9500 Geraardsbergen

Research Institute for Nature and Forest
team Biometrics & Quality Assurance
Gaverstraat 4
9500 Geraardsbergen

tel. + 32 54/436 185
Thierry.Onkelinx at inbo.be

To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of.
~ Sir Ronald Aylmer Fisher

The plural of anecdote is not data.
~ Roger Brinner

The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey

> -----Oorspronkelijk bericht-----
> Van: r-sig-mixed-models-bounces at r-project.org 
> [mailto:r-sig-mixed-models-bounces at r-project.org] Namens Ing. 
> Agr." Agustín Alesso
> Verzonden: vrijdag 10 december 2010 12:38
> Aan: r-sig-mixed-models at r-project.org
> Onderwerp: [R-sig-ME] spatial correlation structure for GLS (nlme)
> Hello,
> I need some advice to include a spatial correlation structure 
> to an ANOVA one-way GLS model. 
> First, I fit a simple model asuming uncorrelated errors and 
> plotted the residuals variogram which showed the spatial 
> autocorrelation. Then, with gstat package, I fit some models 
> to guess initial values for corSpatial.
> The best model fitted has a nugget efect with to spherical 
> structures (2 ranges).
> Before adding more complexity to the model, I tried to fit 
> few models with basic predefined corStructures and then 
> looking at their residuals variograms. Although including 
> correlation results in smaller AICs, the variograms still 
> showing strong spatial correlation of residuals.  
> Is there a way to bluid a spatial correlation structure 
> including two ranges?
> Thanks in advance,
> --
> Ing. Agr. Agustín Alesso
> Dpto. Ciencias del Ambiente
> Fac. Cs. Agrarias - UNL
> Kreder 2805 - S3080HOF - Esperanza
> Tel: 03496-428575 int 337/256
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list 
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

More information about the R-sig-mixed-models mailing list