[R] lme: Variances

[Andrew Robinson]

Hi Hadassa,

> Random effects:
>  Formula: ~1 | id
>         (Intercept) Residual
> StdDev:    4.240752 1.240242
> 
> Correlation Structure: Gaussian spatial correlation
>  Formula: ~age | id 
>  Parameter estimate(s):
>    range 
> 4.662006 

it looks to me as though you have two variance parameters and the
Gaussian variogram.  I speculate that the model that you've written is
not quite the model that you've fit.  I see no provision for sigma
in your lme statement.  Note p. 230 of Pinheiro and Bates, which
says that "The within-group errors can be standardized to have unit
variance, without changing their correlation structure".  Probably 
sigma is confounded with tau.

If my interpretation is correct, then 

nu = 4.240752 
tau = 1.240242 

and tau also has your sigma in there.  Then the p parameter for your
Gaussian semivariogram is 4.662006.

I hope that this helps,

Andrew

-- 
Andrew Robinson                      Ph: 208 885 7115
Department of Forest Resources       Fa: 208 885 6226
University of Idaho                  E : andrewr at uidaho.edu
PO Box 441133                        W : http://www.uidaho.edu/~andrewr
Moscow ID 83843                      Or: http://www.biometrics.uidaho.edu
No statement above necessarily represents my employer's opinion.