Summary of classification accuracy, and percentage of unassigned baseline and adult samples using the Bayesian model averaging (BMA) classifier.

Cross-validated classification accuracy is shown for probability thresholds 0.7 (outside parenthesis) and 0.5 (inside parenthesis). Classification accuracy and percentage of unassigned baseline and adult fish are also shown for the mixed-effect logistic regression classifier that included otolith δ18O and δ13C as predictors and accounted for year-class effects as a random intercept [63], and the Random Forest classifier that relied only on δ18O values [61].