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

$tol0.005
        Fitness JTT Neutral
Fitness      94   0       6
JTT           1  90       9
Neutral       0   0     100


Mean model posterior probabilities (rejection)

$tol0.005
        Fitness    JTT Neutral
Fitness  0.8989 0.0279  0.0732
JTT      0.0420 0.8885  0.0695
Neutral  0.0472 0.0387  0.9141




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, JTT, Neutral
Models a posteriori:
 Fitness, JTT, Neutral

Proportion of accepted simulations (rejection):
Fitness     JTT Neutral 
 0.0133  0.2467  0.7400 

Bayes factors:
        Fitness     JTT Neutral
Fitness  1.0000  0.0541  0.0180
JTT     18.5000  1.0000  0.3333
Neutral 55.5000  3.0000  1.0000





Goodness of fit of Real data

   -Fitness:
$pvalue
[1] 0.27

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.267   3.623   3.963   5.378   4.645  26.778 

$dist.obs
[1] 4.549156

   -JTT:
$pvalue
[1] 0.43

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.240   3.558   3.836   4.305   4.364  10.692 

$dist.obs
[1] 4.053515

   -Neutral:
$pvalue
[1] 0.28

$s.dist.sim
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  3.447   3.863   4.184   5.057   4.813  26.171 

$dist.obs
[1] 4.625982

