Model selection with abc - cross validation - based on 100 samples
Confusion matrix based on 100 samples for each model.

$tol0.005
        Fitness Neutral WAG
Fitness      94       4   2
Neutral       1      99   0
WAG           8       6  86


Mean model posterior probabilities (rejection)

$tol0.005
        Fitness Neutral    WAG
Fitness  0.8637  0.0699 0.0664
Neutral  0.0751  0.9004 0.0245
WAG      0.0790  0.0424 0.8786




Model selection with abc - Real data
Call: 
postpr(target = FullRealmatrix, index = ModelsVector, sumstat = FullSSmatrix, 
    tol = ABC_Tolerance, method = ABC_Method)
Data:
 postpr.out$values (150 posterior samples)
Models a priori:
 Fitness, Neutral, WAG
Models a posteriori:
 Fitness, Neutral, WAG

Proportion of accepted simulations (rejection):
Fitness Neutral     WAG 
 0.9667  0.0333  0.0000 

Bayes factors:
        Fitness Neutral     WAG
Fitness  1.0000 29.0000     Inf
Neutral  0.0345  1.0000     Inf
WAG      0.0000  0.0000        





Goodness of fit of Real data

   -Fitness:
$pvalue
[1] 0.15

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.773   4.147   4.576   5.816   5.174  33.543 

$dist.obs
[1] 5.799146

   -Neutral:
$pvalue
[1] 0.03

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.649   3.954   4.229   4.690   4.698  18.800 

$dist.obs
[1] 10.66472

   -WAG:
$pvalue
[1] 0.46

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.573   3.843   4.193   5.544   5.118  36.023 

$dist.obs
[1] 4.302438

