> library(nlme)
> fm1 <- gls(follicles ~ sin(2*pi*Time) + cos(2*pi*Time), Ovary,
+ correlation = corARMA(form = ~ 1 | Mare, p =
2))> summary(fm1)
Generalized least squares fit by REML
Model: follicles ~ sin(2 * pi * Time) + cos(2 * pi * Time)
Data: Ovary
AIC BIC logLik
1561.995 1584.317 -774.9976
Correlation Structure: ARMA(2,0)
Formula: ~1 | Mare
Parameter estimate(s):
Phi1 Phi2
0.5991803 0.2028649
Coefficients:
Value Std.Error t-value p-value
(Intercept) 12.110836 0.7633842 15.864667 0.0000
sin(2 * pi * Time) -2.825762 0.5773713 -4.894185 0.0000
cos(2 * pi * Time) -0.838151 0.6432846 -1.302924 0.1936
Correlation:
(Intr) s(*p*T
sin(2 * pi * Time) 0.000
cos(2 * pi * Time) -0.276 0.000
Standardized residuals:
Min Q1 Med Q3 Max
-2.39970879 -0.73304443 -0.02229811 0.64429618 3.19313563
Residual standard error: 4.607767
Degrees of freedom: 308 total; 305 residual> coef(fm1$modelStruct, unconstrained = FALSE)
corStruct.Phi1 corStruct.Phi2
0.5991803 0.2028649
Best,
Renaud
2006/11/6, yyan liu <zhliur at yahoo.com>:> Hi:
> The gls function I used in my code is the following
> fm<-gls(y~x,correlation=corARMA(p=2) )
> My question is how to extact the AR(2) parameters from "fm".
> The object "fm" is the following. How can I extract the
correlation parameters
> Phi1 and Phi2 from "fm"? These two parametrs is not in the
"coef" componenet of "fm".
> Thanks a lot!
>
> liu
>
--------------------------------------------------------------------------------------------------------------
> > fm
> Generalized least squares fit by REML
> Model: y ~ x
> Data: NULL
> Log-restricted-likelihood: -1634.588
>
> Coefficients:
> (Intercept) x
> 16.0728672 0.2917921
>
> Correlation Structure: ARMA(2,0)
> Formula: ~1
> Parameter estimate(s):
> Phi1 Phi2
> 1.3368230 -0.4539957
> Degrees of freedom: 480 total; 478 residual
> Residual standard error: 20.80244
>
--------------------------------------------------------------------------------------------------------------
>
>
> ---------------------------------
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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
> and provide commented, minimal, self-contained, reproducible code.
>
--
Renaud LANCELOT
D?partement Elevage et M?decine V?t?rinaire (EMVT) du CIRAD
Directeur adjoint charg? des affaires scientifiques
CIRAD, Animal Production and Veterinary Medicine Department
Deputy director for scientific affairs
Campus international de Baillarguet
TA 30 / B (B?t. B, Bur. 214)
34398 Montpellier Cedex 5 - France
T?l +33 (0)4 67 59 37 17
Secr. +33 (0)4 67 59 39 04
Fax +33 (0)4 67 59 37 95