Identification of blood immune and metabolic indicators explaining the variability of growth of pigs under contrasted sanitary conditions

Table 3 Metrics for the minimal model (rADG_W0-W6 ~ FFA + BAP + HAPTO + ILE + TRP + 1-MH)^a with the training set, its 10 folds repeated 10 times and with the testing set (validation set)

Models	R²	sd R²	R² adjusted	sd R² adjusted	RMSE	sd RMSE	MAE	sd MAE
Training set	0.683		0.664		3.87		3.187
Training set k folds	0.648	0.176	0.629	0.131	4.1	0.813	3.422	0.698
Testing set	0.647		0.566		4.29		3.372

No standard deviation can be estimated for the training and the testing set
R² R-squared, Sd R² Standard deviation of R-squared, R² adjusted Adjusted R squared, Sd R² adjusted Standard deviation of Adjusted R squared, RMSE Root Mean Square Error, Sd RMSE Standard deviation of Root Mean Square Error, MAE Mean Absolute Value, Sd MAE Standard deviation of Mean Absolute Error
^aThe model predicted relative ADG measured during the 6 weeks of the testing period (rADG_W0-W6). The variables are changes in the concentrations in plasma between two times W0 and W3 calculated as concentrations at W3 minus concentrations at W0 for free fatty acids or FFA, Biological Antioxidant Potential or BAP, haptoglobin or HAPTO, isoleucine or ILE, tryptophan or TRP, 1-methylhistidine or 1-MH

ISSN: 1746-6148