[R-sig-ME] Standard errors or t values from glmm.admb

Roberto Patuelli roberto.patuelli at usi.ch
Tue Jun 22 10:42:49 CEST 2010


Dear All,

I have experimented with estimating a negative binomial mixed model through 
the glmmADMB package (that is, using the glmm.admb function).
After an entire night of computing :) I have results (though with a warning 
message saying that proper convergence could not be reached). But when I use 
summary.glmm.admb, I can only see, with regard to the fixed effects, the 
betas estimates, but no standard errors or other measures regarding the 
precision of the regression coefficients. See below:

***********************************************************
Fixed effects:
  Log-likelihood: -12729.3
  Formula: trade ~ factor(YEAR) + factor(contig) + factor(comlang_off) + 
factor(colony) + factor(comcol) + factor(col45) + factor(smctry) + 
log(dist) + log(I(iPopulation * iGDPpcPPP)) + log(I(jPopulation * 
jGDPpcPPP)) + factor(FTA) + log(iPiracy) + log(jPiracy) +      e8 + e14 + 
e15 + e45 + e53 + e57
                    (Intercept)                factor(YEAR)1997 
factor(YEAR)1998                factor(YEAR)1999 
factor(YEAR)2000
                     -5.5350000                       0.0139690 
0.0368520                       0.1594000                       0.2116200
               factor(YEAR)2001                factor(YEAR)2002 
factor(YEAR)2003                factor(YEAR)2004 
factor(YEAR)2005
                      0.2161600                       0.3880400 
0.4666700                       0.5722600                       0.5980400
               factor(YEAR)2006                 factor(contig)1 
factor(comlang_off)1                 factor(colony)1 
factor(comcol)1
                      0.5235100                       0.4576100 
0.6817900                       0.1317700                      -0.0158100
                 factor(col45)1                 factor(smctry)1 
log(dist) log(I(iPopulation * iGDPpcPPP)) log(I(jPopulation * jGDPpcPPP))
                     -0.5674800                      -1.2061000              
         -0.4347800                       0.3970300 
0.3670800
                   factor(FTA)1                    log(iPiracy) 
log(jPiracy)                              e8                             e14
                      0.3087500                      -0.1044300              
         -0.1283700                      -0.1780900                      -0.3323800
                            e15                             e45 
e53                             e57
                     -0.0052419                      -0.2903100              
         -0.1977900                      -0.0892520
***********************************************************

Is anyone more expert than me with this package and can help me getting the 
additional information? Or is it just not given? The help files for the 
package don't seem to help...

Thanks
Roberto Patuelli

********************
Roberto Patuelli, Ph.D.
Istituto Ricerche Economiche (IRE) (Institute for Economic Research)
Università della Svizzera Italiana (University of Lugano)
via Maderno 24, CP 4361
CH-6904 Lugano
Switzerland
Phone: +41-(0)58-666-4166
Fax: +39-02-700419665
Email: roberto.patuelli at usi.ch
Homepage: http://www.people.lu.unisi.ch/patuellr




More information about the R-sig-mixed-models mailing list