R version 3.2.2 (2015-08-14) -- "Fire Safety"
Copyright (C) 2015 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

  Natural language support but running in an English locale

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> 
>  library(glmbb)
>  data(crabs)
> 
>  gout <- glmbb(satell ~ color * spine * width * weight,
+      criterion = "AICc", cutoff = 0, data = crabs)
Warning messages:
1: glm.fit: fitted rates numerically 0 occurred 
2: glm.fit: fitted rates numerically 0 occurred 
3: glm.fit: fitted rates numerically 0 occurred 
4: glm.fit: fitted rates numerically 0 occurred 
>  sout <- summary(gout)
>  sout

Results of search for hierarchical models with lowest AICc.
Search was for all models with AICc no larger than min(AICc) + 0
These are shown below.

  criterion  weight  formula                            
  899.4      1       satell ~ color*spine + spine*weight

> 
>  form <- sout$results$formula
>  form
[1] "satell ~ color*spine + spine*weight"
> 
>  gout.over <- glm(as.formula(form), family = quasipoisson, data = crabs)
>  summary(gout.over)

Call:
glm(formula = as.formula(form), family = quasipoisson, data = crabs)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-3.3010  -1.8168  -0.4221   0.9187   4.7329  

Coefficients:
                          Estimate Std. Error t value Pr(>|t|)    
(Intercept)             -1.182e+00  5.565e-01  -2.124 0.035185 *  
colordarker              1.954e-01  3.366e-01   0.580 0.562407    
colorlight              -1.620e+01  2.269e+03  -0.007 0.994310    
colormedium              3.125e-01  2.439e-01   1.281 0.201933    
spinegood                1.977e+00  8.968e-01   2.204 0.028965 *  
spinemiddle             -1.639e+00  2.688e+00  -0.610 0.542903    
weight                   8.016e-04  2.096e-04   3.824 0.000189 ***
colordarker:spinegood   -1.717e+01  2.269e+03  -0.008 0.993973    
colorlight:spinegood     1.602e+01  2.269e+03   0.007 0.994373    
colormedium:spinegood   -7.956e-01  5.456e-01  -1.458 0.146783    
colordarker:spinemiddle -1.496e+01  2.269e+03  -0.007 0.994745    
colorlight:spinemiddle   1.788e+01  2.269e+03   0.008 0.993722    
colormedium:spinemiddle  4.749e-01  1.127e+00   0.421 0.674087    
spinegood:weight        -4.841e-04  2.864e-04  -1.690 0.092984 .  
spinemiddle:weight       4.349e-04  8.682e-04   0.501 0.617097    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for quasipoisson family taken to be 3.162279)

    Null deviance: 632.79  on 172  degrees of freedom
Residual deviance: 511.06  on 158  degrees of freedom
AIC: NA

Number of Fisher Scoring iterations: 13

> 
>  # apparently, quite a lot of overdispersion
> 
>  # maybe we should have used family quasipoisson with glmbb,
>  # although I am not sure R calculates AIC correctly with quasi-likelihood
> 
>  AIC(gout.over)
[1] NA
>  BIC(gout.over)
[1] NA
> 
>  # it doesn't, so that won't work.
> 
> 
> 
> proc.time()
   user  system elapsed 
  1.436   0.028   1.557