Skip to main content
. 2022 Apr 29;13:827008. doi: 10.3389/fpsyg.2022.827008

Table 4.

The performance and test–retest reliability of regression models.

Method r RMSE R2 Reliability
Model1 GPR 0.44** 1.10 0.17 0.67
Model2 RF 0.20** 1.20 0.01 0.56

r” is the Pearson's correlation coefficient between predicted values and true values (**p < 0.01), and “RMSE” is the root mean square error. R2 is the proportion of the variance in the response variable that can be explained by the predictor variables in the model. GPR, Gaussian process regression; RF, random forest.