Table 14.

Prediction performance of MLR model.

Subject	1	2	3	4	5	6	7	8	9	10
True score	−1.67	−1.09	−0.65	−0.45	−0.01	1.429	1.664	2.306	2.93	3.439
Predicted score	−1.71	−1.24	−0.77	−0.51	−0.03	1.387	1.625	2.415	3.079	3.538

The results of the t-test showed that there was no significant difference between the true and predicted scores, with sig. = 0.99 > 0.5. Furthermore, the coefficient of determination $R^2$ for the prediction sample was 0.997, indicating that the MLR model was of superior goodness of fit and high accuracy for prediction.