Table 4.
Performance metrics associated with each of the five modeling algorithms for each species. AUC ranges correspond to the upper and lower bounds of a 95% CI calculated from across the 10-fold cross validation.
| Threshold 1 | AUC 2 (95% C.I.) | s.e. 3 | Accuracy 4 (95% C.I.) | Kappa 5 | Sensitivity 6 | Specificity 7 | Positive Predictive Value 8 | Negative Predictive Value 9 | |
|---|---|---|---|---|---|---|---|---|---|
| Amblyomma americanum | |||||||||
| Logistic | 0.18 | 0.90 (0.87–0.93) | 0.0152 | 0.828 (0.794–0.859) | 0.525 | 0.827 | 0.829 | 0.506 | 0.957 |
| BRT | 0.26 | 0.92 (0.89–0.95) | 0.0143 | 0.934 (0.91–0.953) | 0.792 | 0.939 | 0.933 | 0.748 | 0.986 |
| RF | 0.23 | 0.92 (0.89–0.95) | 0.0151 | 0.916 (0.89–0.938) | 0.749 | 0.959 | 0.907 | 0.686 | 0.991 |
| MARS | 0.3 | 0.92 (0.89–0.94) | 0.0132 | 0.889 (0.86–0.914) | 0.660 | 0.847 | 0.898 | 0.638 | 0.965 |
| MaxEnt | 0.13 | 0.89 (0.85–0.92) | 0.0168 | 0.617 (0.575–0.658) | 0.276 | 0.959 | 0.544 | 0.309 | 0.984 |
| Ixodes scapularis | |||||||||
| Logistic | 0.14 | 0.83 (0.78–0.88) | 0.0254 | 0.923 (0.898–0.944) | 0.693 | 0.923 | 0.923 | 0.612 | 0.989 |
| BRT | 0.16 | 0.88 (0.83–0.92) | 0.0227 | 0.794 (0.758–0.827) | 0.367 | 0.785 | 0.796 | 0.336 | 0.966 |
| RF | 0.09 | 0.90 (0.86–0.93) | 0.0188 | 0.878 (0.848–0.904) | 0.593 | 1.000 | 0.862 | 0.489 | 1.000 |
| MARS | 0.15 | 0.84 (0.78–0.89) | 0.0279 | 0.875 (0.844–0.901) | 0.524 | 0.785 | 0.887 | 0.477 | 0.969 |
| MaxEnt | 0.24 | 0.85 (0.80–0.90) | 0.0241 | 0.556 (0.514–0.598) | 0.166 | 0.923 | 0.508 | 0.198 | 0.980 |
| Dermacentor variabilis | |||||||||
| Logistic | 0.06 | 0.82 (0.77–0.87) | 0.0246 | 0.809 (0.773–0.84) | 0.244 | 0.800 | 0.809 | 0.192 | 0.986 |
| BRT | 0.1 | 0.82 (0.76–0.88) | 0.0301 | 0.952 (0.931–0.968) | 0.659 | 0.967 | 0.951 | 0.527 | 0.998 |
| RF | 0.04 | 0.83 (0.78–0.88) | 0.0265 | 0.86 (0.829–0.888) | 0.383 | 1.000 | 0.853 | 0.278 | 1.000 |
| MARS | 0.14 | 0.77 (0.69–0.86) | 0.0424 | 0.916 (0.89–0.938) | 0.443 | 0.733 | 0.926 | 0.361 | 0.984 |
| MaxEnt | 0.14 | 0.76 (0.69–0.83) | 0.0355 | 0.358 (0.318–0.399) | 0.044 | 0.967 | 0.323 | 0.075 | 0.994 |
1 Continuous probability score used to delineate presence from absence for consensus predictions (sensitivity = specificity); 2 area under the Receiver Operating Characteristics (ROC) curve; 3 standard error of AUC; 4 ratio of sum of correctly predicted positives and negatives to the sample size; 5 Kohen’s Kappa, a measure of agreement that accounts for agreement due to chance; 6 true positive rate; 7 true negative rate; 8 proportion of positives that are true positives; 9 proportion of negatives that are true negatives.