Skip to main content

Table 3 Best-fitted MR models developed in the current study to predict growth performance of growing-finishing pigs1

From: Predicting the growth performance of growing-finishing pigs based on net energy and digestible lysine intake using multiple regression and artificial neural networks models

Performance

Models2

R2

AIC

BIC

RMSE

ADG

= 57 - 1.63 × BW + 25.42 × SID Lys - 0.360 × SID Lys2 + 0.120 × NE - 4.630 × 10-6 × NE2

0.929

3278

3381

72

F/G

= 1.31 + 1.955 × 10-2 × BW + 9.064 × 10-5 × BW2 - 4.764 × 10-2 × SID Lys + 2.10 × 10-4 NE

0.886

92

116

0.28

  1. ADG average daily gain, AIC akaike information criteria, BIC bayesian information criteria, BW body weight, F/G feed conversion ratio, NE net energy, RMSE root mean square error, SID Lys standardized ileal digestible lysine.
  2. 1 The SID Lys and NE in the equations were the SID Lys intake and NE intake.
  3. 2 The variables in the equations were selected by a P-value < 0.01. Both the best-fitted MR models were generated using the training data set (n = 287).