Regression models evaluation for estimating the body weight of Limousin bulls utilizing its body measurements

Abstract This study aimed to evaluate the correlation and identify the most effective regression model for predicting the body weight of Limousin bulls using body measurements. Data were collected from 50 Limousin bulls, aged 2 to 14 years, at the Lembang Artificial Insemination Center in West Java. The analysis involved simple and multiple regression methods using the R program. Criteria for selecting the best model included correlation coefficient (r), coefficient of determination (R 2 ), Adjusted R 2 , residual standard error (RSE), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The average body weight (BW), chest girth (CG), body length (BL), and shoulder height (SH) were 827.04 ± 123.73 kg, 217.23 ± 15.10 cm, 172.04 ± 11.40 cm, and 142.28 ± 8.12 cm, respectively. Strong correlations were found between BW and CG (r = 0.907), BL (r = 0.811), and SH (r = 0.819). The best regression model for predicting BW combined CG and BL, yielding the highest r and Adjusted R 2 with the lowest RSE, AIC, and BIC. However, considering multicollinearity, the simplest and most effective model was BW = −699.16 + 7.026 CG, suggesting chest girth as a reliable selection criterion.