[R] glmmPQL

[jmgreyes@ugr.es]

Hi,

My name is José María Gómez, and I am pretty new in R. Thus, I apologize
deeply if my questions are extremmely naïve.I have checked several
available books and URL's, without finding any answer.

I'm trying to fit Generalized Linear Mixed Models via PQL. Below I provide
the structure of my data set. Year and Plot are random variables. Fate is
the binomial dependent. I have severe problems after calling glmmPQL:

1) I would like to nest Plot within Year, but I don't know how to argument
it.

2) I'm not sure the analysis I fit (see below) is actually considering
Year and Plot as random.

3) No way to obtain an analysis of deviance for the GLMM fit.

4) Year appears without degrees of freedom.

As you see, too many problems. Thank you very much for any help.
JM
_____________________________________________

> summary (Ifate)
 Year    Plot        Fate         Hab           Peso             Dist
 A:664   A:359   cache :  91   Oak  :621   Min.   :0.1903   Min.   :1.362
 B:574   B:427   comida:1147   Open : 94   1st Qu.:0.5515   1st Qu.:1.847
         C:135                 Pine :159   Median :0.6670   Median :2.137
         D: 97                 Rock : 23   Mean   :0.6674   Mean   :2.200
         E:220                 Shrub:341   3rd Qu.:0.7597   3rd Qu.:2.476
                                           Max.   :1.1386   Max.   :3.872
> library (MASS)
> library (nlme)
> f1<-glmmPQL(Fate~Year+Plot+Hab+Peso+Dist, random=~1|Year/Plot,
family=binomial, data=Ifate)

> anova.glm(f1)
Error in eval(expr, envir, enclos) : Object "Fate" not found

> anova(f1)
            numDF denDF   F-value p-value
(Intercept)     1  1223 124.10634  <.0001
Year            1     0   0.00271     NaN
Plot            4     3   0.96230  0.5343
Hab             4  1223   6.03162  0.0001
Peso            1  1223   4.34225  0.0374
Dist            1  1223   5.97248  0.0147
Warning messages:
1: NaNs produced in: pf(q, df1, df2, lower.tail, log.p)
2: NAs introduced by coercion