Indicator-level out-of-sample prediction
| Model | Outcome | PLS RMSE | LM RMSE | ΔRMSE | PLS MAE | LM MAE | Lower PLS RMSE |
|---|---|---|---|---|---|---|---|
| M1 | FAIR | 0.760 | 0.772 | −0.012 | 0.570 | 0.578 | 2/2 |
| M1 | ACC | 0.768 | 0.784 | −0.016 | 0.578 | 0.589 | 3/3 |
| M1 | TRANS | 0.730 | 0.766 | −0.036 | 0.542 | 0.567 | 3/3 |
| M1 | TRUST | 0.690 | 0.692 | −0.002 | 0.518 | 0.513 | 1/3 |
| M1 | Overall | 0.735 | 0.752 | −0.017 | 0.551 | 0.560 | 9/11 |
| M2A | FAIR | 0.761 | 0.769 | −0.008 | 0.573 | 0.579 | 2/2 |
| M2A | ACC | 0.772 | 0.784 | −0.012 | 0.581 | 0.589 | 3/3 |
| M2A | TRANS | 0.733 | 0.759 | −0.026 | 0.548 | 0.564 | 3/3 |
| M2A | TRUST | 0.691 | 0.697 | −0.006 | 0.519 | 0.516 | 2/3 |
| M2A | Overall | 0.737 | 0.751 | −0.013 | 0.554 | 0.561 | 10/11 |
| M2B | FAIR | 0.764 | 0.769 | −0.005 | 0.574 | 0.577 | 1/2 |
| M2B | ACC | 0.774 | 0.794 | −0.020 | 0.582 | 0.598 | 3/3 |
| M2B | TRANS | 0.742 | 0.771 | −0.028 | 0.548 | 0.570 | 3/3 |
| M2B | TRUST | 0.693 | 0.701 | −0.008 | 0.520 | 0.518 | 2/3 |
| M2B | Overall | 0.742 | 0.758 | −0.016 | 0.554 | 0.565 | 9/11 |
| Model | Outcome | PLS RMSE | LM RMSE | ΔRMSE | PLS MAE | LM MAE | Lower PLS RMSE |
|---|---|---|---|---|---|---|---|
| M1 | FAIR | 0.760 | 0.772 | −0.012 | 0.570 | 0.578 | 2/2 |
| M1 | ACC | 0.768 | 0.784 | −0.016 | 0.578 | 0.589 | 3/3 |
| M1 | TRANS | 0.730 | 0.766 | −0.036 | 0.542 | 0.567 | 3/3 |
| M1 | TRUST | 0.690 | 0.692 | −0.002 | 0.518 | 0.513 | 1/3 |
| M1 | Overall | 0.735 | 0.752 | −0.017 | 0.551 | 0.560 | 9/11 |
| M2A | FAIR | 0.761 | 0.769 | −0.008 | 0.573 | 0.579 | 2/2 |
| M2A | ACC | 0.772 | 0.784 | −0.012 | 0.581 | 0.589 | 3/3 |
| M2A | TRANS | 0.733 | 0.759 | −0.026 | 0.548 | 0.564 | 3/3 |
| M2A | TRUST | 0.691 | 0.697 | −0.006 | 0.519 | 0.516 | 2/3 |
| M2A | Overall | 0.737 | 0.751 | −0.013 | 0.554 | 0.561 | 10/11 |
| M2B | FAIR | 0.764 | 0.769 | −0.005 | 0.574 | 0.577 | 1/2 |
| M2B | ACC | 0.774 | 0.794 | −0.020 | 0.582 | 0.598 | 3/3 |
| M2B | TRANS | 0.742 | 0.771 | −0.028 | 0.548 | 0.570 | 3/3 |
| M2B | TRUST | 0.693 | 0.701 | −0.008 | 0.520 | 0.518 | 2/3 |
| M2B | Overall | 0.742 | 0.758 | −0.016 | 0.554 | 0.565 | 9/11 |
Note(s): Ten-fold PLSpredict with ten repetitions. Values are averages across the indicators belonging to each outcome. LM = linear-model benchmark; ΔRMSE = PLS RMSE minus LM RMSE, so negative values favour PLS. The final column reports the number of indicators for which PLS produced a lower RMSE than the benchmark
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.