[BioC] gls from nlme package not compatible with methods package

James Wettenhall wettenhall@wehi.edu.au
Mon, 13 Jan 2003 16:34:35 +1100 (EST)


Dear Bioconductor,

I am trying to develop a Bioconductor-style package for fitting 
linear models to microarray data, to be used with marrayNorm, 
marrayInput etc.

I want to use the function gls (generalized least squares) from 
the nlme package.  But it doesn't seem to be compatible with the 
methods package.  Any suggestions?

Regards,
James

> y <- rnorm(20)
> x <- 1:20
> library(nlme)
Loading required package: nls
> out <- gls(y~x)
> summary(out)
Generalized least squares fit by REML
  Model: y ~ x
  Data: NULL
       AIC      BIC    logLik
  63.18472 65.85584 -28.59236

Coefficients:
                 Value Std.Error   t-value p-value
(Intercept) -0.4416286 0.4227542 -1.044646  0.3100
x           -0.0004764 0.0352908 -0.013499  0.9894

 Correlation:
  (Intr)
x -0.877

Standardized residuals:
        Min          Q1         Med          Q3         Max
-1.85167510 -0.68224481  0.03176228  0.71367684  1.79529312

Residual standard error: 0.9100658
Degrees of freedom: 20 total; 18 residual
> out <- gls(y~x)
> library(methods)
> out <- gls(y~x)
Error in getClass(Class) : "glsStruct" is not a defined class


 
--------------------------------------------------------------------------
James Wettenhall                                  Tel: (+61 3) 9345 2629
Division of Genetics and Bioinformatics           Fax: (+61 3) 9347 0852
The Walter & Eliza Hall Institute         E-mail: wettenhall@wehi.edu.au
 of Medical Research,                     Mobile: (+61 / 0 ) 438 527 921    
1G Royal Parade,
Parkville, Vic 3050, Australia
http://www.wehi.edu.au
--------------------------------------------------------------------------