R help - Mar 2011 - AIC on GLMM pscl package

Hello,

I'm using GLMM on the pscl package and i'm not getting the AIC on the
summary. 

The code i'm using is (example) :

mmall3 <-glmmPQL(allclues ~ cycloc + male, data=dados, family=poisson,
random=~1|animal/idfid)


and the results:

Linear mixed-effects model fit by maximum likelihood
 Data: dados 
  AIC BIC logLik
   NA  NA     NA

Random effects:
 Formula: ~1 | animal
        (Intercept)
StdDev:   0.4235518

 Formula: ~1 | idfid %in% animal
        (Intercept) Residual
StdDev:    0.947683 1.752526

Variance function:
 Structure: fixed weights
 Formula: ~invwt 
Fixed effects: allclues ~ cycloc + male 
                 Value Std.Error  DF   t-value p-value
(Intercept)  1.8050720 0.2653779 333  6.801892  0.0000
cycloc       0.0718826 0.0128099 181  5.611469  0.0000
male1       -0.6254748 0.3552453   5 -1.760684  0.1386
 Correlation: 
       (Intr) cycloc
cycloc -0.060       
male1  -0.744 -0.008

Standardized Within-Group Residuals:
       Min         Q1        Med         Q3        Max 
-2.8968532 -0.6758671 -0.2687695  0.3338190  4.5704000 

Number of Observations: 522
Number of Groups: 



Am i doing something wrong? Or theres a code to extract the AIC of the
model?

Thanks,
Best regards

Hugo Caribu


--
View this message in context:
http://r.789695.n4.nabble.com/AIC-on-GLMM-pscl-package-tp3335371p3335371.html
Sent from the R help mailing list archive at Nabble.com.

Caribu <hugoazina <at> gmail.com> writes:
> 
> Hello,
> 
> I'm using GLMM on the pscl package and i'm not getting the AIC on
the
> summary. 
> 
 [snip]

 glmmPQL is in the MASS package, not the pscl package.
 Because it uses a quasi-likelihood approach, it does not
provide an AIC value (which technically does not exist in this
case).  It is in principle possible to get a "quasi-AIC",
but it is (a) delicate to define and (b) moderately challenging
to extract the information from glmmPQL.

  Ben Bolker