Marios Frog ABC with 2 Models
1 Model selection for all species and populations
After choosing the ABC rejection+regression algorithm, a set of summary statistics, generating more simulations for no mask and tweaking the priors a little, I started doing the model selection for all of the populations and species. Here are the results.
Here are all the results and how they are generated in detail, including cross validation and other stuff. Just expand what you are interested in. In the end is a summary table.
call GH
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 66 34
## exp 38 62
##
## $tol0.02
## con exp
## con 63 37
## exp 33 67
##
## $tol0.05
## con exp
## con 61 39
## exp 33 67
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6585 0.3415
## exp 0.3563 0.6437
##
## $tol0.02
## con exp
## con 0.6423 0.3577
## exp 0.3575 0.6425
##
## $tol0.05
## con exp
## con 0.6210 0.3790
## exp 0.3724 0.6276Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (76 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.6184 0.3816
##
## Bayes factors:
## con exp
## con 1.0000 1.6207
## exp 0.6170 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.8335 0.1665
##
## Bayes factors:
## con exp
## con 1.0000 5.0061
## exp 0.1998 1.0000call WUG1
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 74 26
## exp 35 65
##
## $tol0.02
## con exp
## con 71 29
## exp 33 67
##
## $tol0.05
## con exp
## con 73 27
## exp 39 61
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.7412 0.2588
## exp 0.3511 0.6489
##
## $tol0.02
## con exp
## con 0.6838 0.3162
## exp 0.3609 0.6391
##
## $tol0.05
## con exp
## con 0.6862 0.3138
## exp 0.3864 0.6136Model Selection:
## Warning: There are 2 models but only 1 for which simulations have been accepted.
## No regression is performed, method is set to rejection.
## Consider increasing the tolerance rate.TRUE## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (77 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 1 0
##
## Bayes factors:
## con exp
## con 1 Inf
## exp 0call WUG2
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 65 35
## exp 28 72
##
## $tol0.02
## con exp
## con 62 38
## exp 24 76
##
## $tol0.05
## con exp
## con 59 41
## exp 25 75
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6591 0.3409
## exp 0.2737 0.7263
##
## $tol0.02
## con exp
## con 0.6093 0.3907
## exp 0.2705 0.7295
##
## $tol0.05
## con exp
## con 0.5956 0.4044
## exp 0.3010 0.6990Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (77 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4545 0.5455
##
## Bayes factors:
## con exp
## con 1.0000 0.8333
## exp 1.2000 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.4855 0.5145
##
## Bayes factors:
## con exp
## con 1.0000 0.9436
## exp 1.0597 1.0000call WUG3
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 58 42
## exp 29 71
##
## $tol0.02
## con exp
## con 47 53
## exp 30 70
##
## $tol0.05
## con exp
## con 44 56
## exp 34 66
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.5591 0.4409
## exp 0.3155 0.6845
##
## $tol0.02
## con exp
## con 0.4933 0.5067
## exp 0.3481 0.6519
##
## $tol0.05
## con exp
## con 0.5005 0.4995
## exp 0.4077 0.5923Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4231 0.5769
##
## Bayes factors:
## con exp
## con 1.0000 0.7333
## exp 1.3636 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.3429 0.6571
##
## Bayes factors:
## con exp
## con 1.0000 0.5217
## exp 1.9167 1.0000call WUG4
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 69 31
## exp 31 69
##
## $tol0.02
## con exp
## con 61 39
## exp 30 70
##
## $tol0.05
## con exp
## con 65 35
## exp 41 59
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6832 0.3168
## exp 0.3160 0.6840
##
## $tol0.02
## con exp
## con 0.6171 0.3829
## exp 0.3279 0.6721
##
## $tol0.05
## con exp
## con 0.6297 0.3703
## exp 0.3784 0.6216Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.5513 0.4487
##
## Bayes factors:
## con exp
## con 1.0000 1.2286
## exp 0.8140 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.6751 0.3249
##
## Bayes factors:
## con exp
## con 1.0000 2.0777
## exp 0.4813 1.0000call WUG5
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 59 41
## exp 40 60
##
## $tol0.02
## con exp
## con 54 46
## exp 41 59
##
## $tol0.05
## con exp
## con 47 53
## exp 39 61
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.5928 0.4072
## exp 0.4031 0.5969
##
## $tol0.02
## con exp
## con 0.5427 0.4573
## exp 0.4016 0.5984
##
## $tol0.05
## con exp
## con 0.5293 0.4707
## exp 0.3910 0.6090Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (75 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4667 0.5333
##
## Bayes factors:
## con exp
## con 1.0000 0.8750
## exp 1.1429 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.2351 0.7649
##
## Bayes factors:
## con exp
## con 1.0000 0.3074
## exp 3.2531 1.0000pall GH
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 67 33
## exp 31 69
##
## $tol0.02
## con exp
## con 60 40
## exp 31 69
##
## $tol0.05
## con exp
## con 65 35
## exp 23 77
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6490 0.3510
## exp 0.3196 0.6804
##
## $tol0.02
## con exp
## con 0.6516 0.3484
## exp 0.3196 0.6804
##
## $tol0.05
## con exp
## con 0.6655 0.3345
## exp 0.3233 0.6767Model Selection:
## Warning: There are 2 models but only 1 for which simulations have been accepted.
## No regression is performed, method is set to rejection.
## Consider increasing the tolerance rate.TRUE## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 1 0
##
## Bayes factors:
## con exp
## con 1 Inf
## exp 0pall WUG1
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 64 36
## exp 28 72
##
## $tol0.02
## con exp
## con 59 41
## exp 24 76
##
## $tol0.05
## con exp
## con 58 42
## exp 19 81
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6318 0.3682
## exp 0.2883 0.7117
##
## $tol0.02
## con exp
## con 0.5983 0.4017
## exp 0.2785 0.7215
##
## $tol0.05
## con exp
## con 0.5959 0.4041
## exp 0.2801 0.7199Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (77 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4545 0.5455
##
## Bayes factors:
## con exp
## con 1.0000 0.8333
## exp 1.2000 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.6916 0.3084
##
## Bayes factors:
## con exp
## con 1.0000 2.2427
## exp 0.4459 1.0000pall WUG2
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 62 38
## exp 36 64
##
## $tol0.02
## con exp
## con 62 38
## exp 30 70
##
## $tol0.05
## con exp
## con 58 42
## exp 25 75
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6211 0.3789
## exp 0.3677 0.6323
##
## $tol0.02
## con exp
## con 0.6337 0.3663
## exp 0.3471 0.6529
##
## $tol0.05
## con exp
## con 0.6067 0.3933
## exp 0.3463 0.6537Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.5256 0.4744
##
## Bayes factors:
## con exp
## con 1.0000 1.1081
## exp 0.9024 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.7528 0.2472
##
## Bayes factors:
## con exp
## con 1.0000 3.0454
## exp 0.3284 1.0000plib GH
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 66 34
## exp 36 64
##
## $tol0.02
## con exp
## con 60 40
## exp 31 69
##
## $tol0.05
## con exp
## con 60 40
## exp 26 74
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6305 0.3695
## exp 0.3593 0.6407
##
## $tol0.02
## con exp
## con 0.6101 0.3899
## exp 0.3752 0.6248
##
## $tol0.05
## con exp
## con 0.6206 0.3794
## exp 0.3841 0.6159Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4872 0.5128
##
## Bayes factors:
## con exp
## con 1.0000 0.9500
## exp 1.0526 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.7471 0.2529
##
## Bayes factors:
## con exp
## con 1.0000 2.9544
## exp 0.3385 1.0000plib WUG1
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 63 37
## exp 40 60
##
## $tol0.02
## con exp
## con 67 33
## exp 48 52
##
## $tol0.05
## con exp
## con 77 23
## exp 46 54
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.6248 0.3752
## exp 0.4030 0.5970
##
## $tol0.02
## con exp
## con 0.6545 0.3455
## exp 0.4665 0.5335
##
## $tol0.05
## con exp
## con 0.6549 0.3451
## exp 0.4718 0.5282Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (77 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4156 0.5844
##
## Bayes factors:
## con exp
## con 1.0000 0.7111
## exp 1.4062 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.4739 0.5261
##
## Bayes factors:
## con exp
## con 1.0000 0.9007
## exp 1.1103 1.0000ppli GH
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 75 25
## exp 21 79
##
## $tol0.02
## con exp
## con 77 23
## exp 20 80
##
## $tol0.05
## con exp
## con 77 23
## exp 19 81
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.7820 0.2180
## exp 0.2385 0.7615
##
## $tol0.02
## con exp
## con 0.7793 0.2207
## exp 0.2366 0.7634
##
## $tol0.05
## con exp
## con 0.7855 0.2145
## exp 0.2477 0.7523Model Selection:
## Warning: There are 2 models but only 1 for which simulations have been accepted.
## No regression is performed, method is set to rejection.
## Consider increasing the tolerance rate.TRUE## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (77 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 1 0
##
## Bayes factors:
## con exp
## con 1 Inf
## exp 0ppli WUG1
PCA:
Cross validation:
## Confusion matrix based on 100 samples for each model.
##
## $tol0.01
## con exp
## con 75 25
## exp 26 74
##
## $tol0.02
## con exp
## con 73 27
## exp 18 82
##
## $tol0.05
## con exp
## con 80 20
## exp 16 84
##
##
## Mean model posterior probabilities (mnlogistic)
##
## $tol0.01
## con exp
## con 0.7461 0.2539
## exp 0.2530 0.7470
##
## $tol0.02
## con exp
## con 0.7505 0.2495
## exp 0.1815 0.8185
##
## $tol0.05
## con exp
## con 0.7665 0.2335
## exp 0.1837 0.8163Model Selection:
## Call:
## postpr(target = tar, index = model, sumstat = sumstat, tol = 0.02,
## method = "mnlogistic")
## Data:
## postpr.out$values (78 posterior samples)
## Models a priori:
## con, exp
## Models a posteriori:
## con, exp
##
## Proportion of accepted simulations (rejection):
## con exp
## 0.4231 0.5769
##
## Bayes factors:
## con exp
## con 1.0000 0.7333
## exp 1.3636 1.0000
##
##
## Posterior model probabilities (mnlogistic):
## con exp
## 0.7822 0.2178
##
## Bayes factors:
## con exp
## con 1.0000 3.5918
## exp 0.2784 1.00001.1 Summary Table
| con | exp | |
|---|---|---|
| call_GH_pred | 0.8335028 | 0.1664972 |
| call_WUG1_pred | 1.0000000 | 0.0000000 |
| call_WUG2_pred | 0.4855015 | 0.5144985 |
| call_WUG3_pred | 0.3428556 | 0.6571444 |
| call_WUG4_pred | 0.6750805 | 0.3249195 |
| call_WUG5_pred | 0.2351216 | 0.7648784 |
| pall_GH_pred | 1.0000000 | 0.0000000 |
| pall_WUG1_pred | 0.6916146 | 0.3083854 |
| pall_WUG2_pred | 0.7528049 | 0.2471951 |
| plib_GH_pred | 0.7471175 | 0.2528825 |
| plib_WUG1_pred | 0.4738708 | 0.5261292 |
| ppli_GH_pred | 1.0000000 | 0.0000000 |
| ppli_WUG1_pred | 0.7822212 | 0.2177788 |
2 Parameter estimation
Here is the parameter estimation for each population under the best model chosen for it. Again the details in de collapsible and then a a summary table at the end.
call GH
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.9035654
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (141 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -0.9971
## Weighted 2.5 % Perc.: 4.7645
## Weighted Median: 10.6961
## Weighted Mean: 11.0577
## Weighted Mode: 10.5828
## Weighted 97.5 % Perc.: 24.9847
## Max.: 32.8258
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.6695014
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -2509915
## Weighted 2.5 % Perc.: -296049
## Weighted Median: 2024085
## Weighted Mean: 2180918
## Weighted Mode: 1676479
## Weighted 97.5 % Perc.: 4269017
## Max.: 5305529
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.001786882
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 89285.01
## Weighted 2.5 % Perc.: 93088.66
## Weighted Median: 95809.21
## Weighted Mean: 95860.72
## Weighted Mode: 95846.45
## Weighted 97.5 % Perc.: 98333.10
## Max.: 102569.39
call WUG1
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.965598
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 2.2822
## Weighted 2.5 % Perc.: 6.6944
## Weighted Median: 11.8934
## Weighted Mean: 12.5720
## Weighted Mode: 11.0679
## Weighted 97.5 % Perc.: 20.6839
## Max.: 37.4260
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.123282
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -939372.0
## Weighted 2.5 % Perc.: 655486.5
## Weighted Median: 1442157.1
## Weighted Mean: 1541706.5
## Weighted Mode: 1329792.9
## Weighted 97.5 % Perc.: 2690013.5
## Max.: 5244732.3
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.005474869
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 97608.71
## Weighted 2.5 % Perc.: 97942.57
## Weighted Median: 98715.36
## Weighted Mean: 98710.59
## Weighted Mode: 98731.73
## Weighted 97.5 % Perc.: 99447.61
## Max.: 99814.82
call WUG2
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 3.220563
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -92.1096
## Weighted 2.5 % Perc.: -19.8987
## Weighted Median: 12.2911
## Weighted Mean: 23.0172
## Weighted Mode: 5.8569
## Weighted 97.5 % Perc.: 106.8347
## Max.: 542.6684
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.318987
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -1860743.88
## Weighted 2.5 % Perc.: 66735.22
## Weighted Median: 2722357.58
## Weighted Mean: 2802683.01
## Weighted Mode: 2680609.96
## Weighted 97.5 % Perc.: 5785848.45
## Max.: 7901972.17
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.007767491
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 175848.2
## Weighted 2.5 % Perc.: 177007.8
## Weighted Median: 177727.0
## Weighted Mean: 177809.9
## Weighted Mode: 177677.1
## Weighted 97.5 % Perc.: 179028.5
## Max.: 179088.9
call WUG3
Itensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.195392
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 26.9290
## Weighted 2.5 % Perc.: 28.1815
## Weighted Median: 35.1175
## Weighted Mean: 37.9766
## Weighted Mode: 33.5571
## Weighted 97.5 % Perc.: 61.2428
## Max.: 126.8588
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.568512
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -167649.66
## Weighted 2.5 % Perc.: -70496.42
## Weighted Median: 25885.41
## Weighted Mean: 47143.14
## Weighted Mode: 24066.01
## Weighted 97.5 % Perc.: 268748.85
## Max.: 637995.46
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.001305559
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 43643.54
## Weighted 2.5 % Perc.: 87209.11
## Weighted Median: 123715.49
## Weighted Mean: 121541.97
## Weighted Mode: 127346.73
## Weighted 97.5 % Perc.: 149139.92
## Max.: 362551.67
call WUG4
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 3.093037
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 16.8938
## Weighted 2.5 % Perc.: 17.8380
## Weighted Median: 19.0011
## Weighted Mean: 19.2871
## Weighted Mode: 18.8547
## Weighted 97.5 % Perc.: 23.3668
## Max.: 27.3447
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.956668
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -174801.3
## Weighted 2.5 % Perc.: 580222.5
## Weighted Median: 1649959.3
## Weighted Mean: 1715114.9
## Weighted Mode: 1388731.1
## Weighted 97.5 % Perc.: 2843297.8
## Max.: 4019974.8
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.004241838
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 113783.4
## Weighted 2.5 % Perc.: 115117.2
## Weighted Median: 117062.7
## Weighted Mean: 117265.0
## Weighted Mode: 116811.1
## Weighted 97.5 % Perc.: 119894.6
## Max.: 123324.9
call WUG5
PCA:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.911601
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (141 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -86.0987
## Weighted 2.5 % Perc.: -40.3677
## Weighted Median: 11.5007
## Weighted Mean: 17.4672
## Weighted Mode: 8.4755
## Weighted 97.5 % Perc.: 98.9418
## Max.: 314.7245
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 2.209451
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (141 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -857660.8
## Weighted 2.5 % Perc.: 918211.2
## Weighted Median: 4689050.7
## Weighted Mean: 4477665.7
## Weighted Mode: 5636201.1
## Weighted 97.5 % Perc.: 8675190.7
## Max.: 10256582.6
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.01055754
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (141 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 155646.4
## Weighted 2.5 % Perc.: 162282.5
## Weighted Median: 163987.1
## Weighted Mean: 164139.8
## Weighted Mode: 163991.0
## Weighted 97.5 % Perc.: 166273.2
## Max.: 167448.3
pall GH
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.8555677
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 0.3938
## Weighted 2.5 % Perc.: 3.0102
## Weighted Median: 9.8233
## Weighted Mean: 11.5719
## Weighted Mode: 6.5801
## Weighted 97.5 % Perc.: 27.7706
## Max.: 53.3300
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.6488283
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 356259.0
## Weighted 2.5 % Perc.: 492787.3
## Weighted Median: 820728.3
## Weighted Mean: 908925.4
## Weighted Mode: 778780.6
## Weighted 97.5 % Perc.: 1791162.9
## Max.: 3885152.5
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.003224946
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 104683.2
## Weighted 2.5 % Perc.: 107849.4
## Weighted Median: 111411.5
## Weighted Mean: 111413.3
## Weighted Mode: 111650.1
## Weighted 97.5 % Perc.: 114698.8
## Max.: 122218.7
pall WUG1
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.189307
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -1.7915
## Weighted 2.5 % Perc.: 0.7737
## Weighted Median: 3.3522
## Weighted Mean: 3.8127
## Weighted Mode: 2.7091
## Weighted 97.5 % Perc.: 8.7084
## Max.: 15.2162
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.7427261
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -131577.2
## Weighted 2.5 % Perc.: 867162.4
## Weighted Median: 1333098.3
## Weighted Mean: 1380349.4
## Weighted Mode: 1282720.7
## Weighted 97.5 % Perc.: 1958623.1
## Max.: 3519187.6
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.0007418628
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 27188.32
## Weighted 2.5 % Perc.: 29036.00
## Weighted Median: 30382.11
## Weighted Mean: 30398.10
## Weighted Mode: 30340.76
## Weighted 97.5 % Perc.: 31541.88
## Max.: 33984.40
pall WUG2
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.283253
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -3.4531
## Weighted 2.5 % Perc.: 0.2956
## Weighted Median: 4.1471
## Weighted Mean: 4.4877
## Weighted Mode: 3.3597
## Weighted 97.5 % Perc.: 10.3669
## Max.: 21.9005
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.379242
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 389628.7
## Weighted 2.5 % Perc.: 484876.3
## Weighted Median: 1339077.9
## Weighted Mean: 1419101.9
## Weighted Mode: 1207215.1
## Weighted 97.5 % Perc.: 2263743.9
## Max.: 3041870.7
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.0008907214
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 55304.46
## Weighted 2.5 % Perc.: 55488.33
## Weighted Median: 56060.72
## Weighted Mean: 56083.45
## Weighted Mode: 56016.71
## Weighted 97.5 % Perc.: 56668.65
## Max.: 60083.71
plib GH
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.07111
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -13.5975
## Weighted 2.5 % Perc.: -1.0867
## Weighted Median: 10.7735
## Weighted Mean: 14.7953
## Weighted Mode: 7.2927
## Weighted 97.5 % Perc.: 44.0808
## Max.: 93.3119
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.9436518
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -1111080.6
## Weighted 2.5 % Perc.: -653286.8
## Weighted Median: 376375.8
## Weighted Mean: 489341.4
## Weighted Mode: 247430.2
## Weighted 97.5 % Perc.: 1695358.8
## Max.: 4210778.1
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.000558175
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (147 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 56506.80
## Weighted 2.5 % Perc.: 57281.19
## Weighted Median: 59439.95
## Weighted Mean: 59380.23
## Weighted Mode: 59069.61
## Weighted 97.5 % Perc.: 61201.96
## Max.: 63230.27
plib WUG1
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 1.21034
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -27.8009
## Weighted 2.5 % Perc.: 2.0602
## Weighted Median: 13.1398
## Weighted Mean: 13.0759
## Weighted Mode: 14.6391
## Weighted 97.5 % Perc.: 33.3561
## Max.: 61.2708
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.8869884
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 368426.6
## Weighted 2.5 % Perc.: 484148.9
## Weighted Median: 974617.1
## Weighted Mean: 1051975.4
## Weighted Mode: 956341.4
## Weighted 97.5 % Perc.: 1869232.8
## Max.: 2228232.3
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.001302433
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 150127.3
## Weighted 2.5 % Perc.: 153841.5
## Weighted Median: 158347.5
## Weighted Mean: 158701.6
## Weighted Mode: 157594.3
## Weighted 97.5 % Perc.: 164335.2
## Max.: 173950.1
ppli GH
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.831156
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (145 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 18.0741
## Weighted 2.5 % Perc.: 19.5539
## Weighted Median: 22.8861
## Weighted Mean: 23.9184
## Weighted Mode: 22.2426
## Weighted 97.5 % Perc.: 31.6106
## Max.: 53.7988
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.3143715
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 73016.57
## Weighted 2.5 % Perc.: 74600.54
## Weighted Median: 108320.43
## Weighted Mean: 108294.75
## Weighted Mode: 105920.66
## Weighted 97.5 % Perc.: 129809.36
## Max.: 147639.40
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.01932286
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (144 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 128024.3
## Weighted 2.5 % Perc.: 162728.5
## Weighted Median: 183342.4
## Weighted Mean: 184379.9
## Weighted Mode: 181712.6
## Weighted 97.5 % Perc.: 213313.7
## Max.: 246463.4
ppli WUG1
Intensity CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.4313614
Intensity Estimate:
## Warning in abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## : No parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = intensity, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: -4.6636
## Weighted 2.5 % Perc.: -0.3952
## Weighted Median: 5.8707
## Weighted Mean: 7.2356
## Weighted Mode: 4.9749
## Weighted 97.5 % Perc.: 17.2391
## Max.: 55.7916
Time CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.6120778
Time Estimate:
## Warning in abc(target = tar, param = time, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = time, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 1449487
## Weighted 2.5 % Perc.: 1478240
## Weighted Median: 1501960
## Weighted Mean: 1501498
## Weighted Mode: 1493092
## Weighted 97.5 % Perc.: 1524437
## Max.: 1544949
Ne CV:
## Prediction error based on a cross-validation sample of 100## P1
## 0.05 0.003956902
Ne Estimate:
## Warning in abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075, : No
## parameter names are given, using P1, P2, ...## Call:
## abc(target = tar, param = ne, sumstat = sumstat, tol = 0.075,
## method = "loclinear")
## Data:
## abc.out$adj.values (146 posterior samples)
## Weights:
## abc.out$weights## Warning in density.default(x, weights = weights): Selecting bandwidth *not*
## using 'weights'## P1
## Min.: 974.5329
## Weighted 2.5 % Perc.: 1148.0409
## Weighted Median: 1367.6171
## Weighted Mean: 1372.7670
## Weighted Mode: 1353.5939
## Weighted 97.5 % Perc.: 1599.0905
## Max.: 1821.7289
2.1 Summary Table
| population | int | time | ne |
|---|---|---|---|
| call_GH | 10.6960554254761 | 2024084.61401233 | 95809.2107750962 |
| call_WUG1 | 11.8933865804829 | 1442157.09852832 | 98715.3569475382 |
| call_WUG2 | 12.2910724336867 | 2722357.57867628 | 177726.968669022 |
| call_WUG3 | 35.1175028447456 | 25885.407455312 | 123715.489340042 |
| call_WUG4 | 19.0011263738894 | 1649959.34598739 | 117062.670608756 |
| call_WUG5 | 11.5007480228398 | 4689050.65228968 | 163987.118716808 |
| pall_GH | 9.82334330206158 | 820728.317230858 | 111411.542710081 |
| pall_WUG1 | 3.35215465276503 | 1333098.29610666 | 30382.1100609658 |
| pall_WUG2 | 4.14705344180756 | 1339077.87514032 | 56060.7179809008 |
| plib_GH | 10.7734788286851 | 376375.812423616 | 59439.9471473992 |
| plib_WUG1 | 13.139783485328 | 974617.117190744 | 158347.513213599 |
| ppli_GH | 22.8861011176987 | 108320.430142211 | 183342.405295802 |
| ppli_WUG1_ne | 5.87069662704055 | 1501960.3414185 | 1367.61710853065 |