A multilevel nonlinear mixed-effects approach to model growth in pigs

TY - JOUR

T1 - A multilevel nonlinear mixed-effects approach to model growth in pigs

AU - Strathe, Anders Bjerring

AU - Danfær, Allan Christian

AU - Sørensen, Helle

AU - Kebreab, Ermias

PY - 2010/2

Y1 - 2010/2

N2 - Growth functions have been used to predict market weight of pigs and maximize return over feed costs. This study was undertaken to compare 4 growth functions and methods of analyzing data, particularly one that considers nonlinear repeated measures. Data were collected from an experiment with 40 pigs maintained from birth to maturity and their BW measured weekly or every 2 wk up to 1,007 d. Gompertz, logistic, Bridges, and Lopez functions were fitted to the data and compared using information criteria. For each function, a multilevel nonlinear mixed effects model was employed because it allowed for estimation of all growth profiles simultaneously, and different sources of variation (i.e., sex, pig, and litter effects) were incorporated directly into the parameters. Furthermore, variance in-homogeneity and within-pig correlation were introduced to the functions. Inclusion of a variance of power function and a continuous autoregressive process of first order rendered a substantially improved fit to data for all 4 growth functions. The Lopez function provided the best fit to the data set and was used for characterizing mean growth curves for the 3 sexes (barrows, boars, and gilts). It was estimated that the maximum growth rate occurs at 117, 134, and 96 kg of BW for barrows, boars, and gilts, respectively. Hence, the gilts reached their maximum growth rate at an earlier stage in life compared with boars. Mature size of pigs varied systematically with sex and was estimated to be 466, 537, and 382 kg of BW for the barrows, boars, and gilts, respectively. These estimates are significantly affected by the duration of the experimental period, and it is recommended that future studies looking at estimating the mature size in animals are conducted long enough so that the BW visually stabilizes. Furthermore, studies should consider adding continuous autoregressive process when analyzing non-linear mixed models with repeated measures.

AB - Growth functions have been used to predict market weight of pigs and maximize return over feed costs. This study was undertaken to compare 4 growth functions and methods of analyzing data, particularly one that considers nonlinear repeated measures. Data were collected from an experiment with 40 pigs maintained from birth to maturity and their BW measured weekly or every 2 wk up to 1,007 d. Gompertz, logistic, Bridges, and Lopez functions were fitted to the data and compared using information criteria. For each function, a multilevel nonlinear mixed effects model was employed because it allowed for estimation of all growth profiles simultaneously, and different sources of variation (i.e., sex, pig, and litter effects) were incorporated directly into the parameters. Furthermore, variance in-homogeneity and within-pig correlation were introduced to the functions. Inclusion of a variance of power function and a continuous autoregressive process of first order rendered a substantially improved fit to data for all 4 growth functions. The Lopez function provided the best fit to the data set and was used for characterizing mean growth curves for the 3 sexes (barrows, boars, and gilts). It was estimated that the maximum growth rate occurs at 117, 134, and 96 kg of BW for barrows, boars, and gilts, respectively. Hence, the gilts reached their maximum growth rate at an earlier stage in life compared with boars. Mature size of pigs varied systematically with sex and was estimated to be 466, 537, and 382 kg of BW for the barrows, boars, and gilts, respectively. These estimates are significantly affected by the duration of the experimental period, and it is recommended that future studies looking at estimating the mature size in animals are conducted long enough so that the BW visually stabilizes. Furthermore, studies should consider adding continuous autoregressive process when analyzing non-linear mixed models with repeated measures.

M3 - Journal article

SN - 0021-8812

VL - 88

SP - 638

EP - 649

JO - Journal of Animal Science

JF - Journal of Animal Science

ER -