Analysis of Growth Performance Data in Sidama Goats using Fixed and Random Regression Models

Most statistical approaches in experiments of feeding trial are based on the analysis of variance (ANOVA) and least square regressions. However, most of the time, the assumption that data are independent is violated since several measurements are taken on the same subject (repeated measures). In addition, the presence of intra- and interobservers variability can potentially obscure significant differences.

In this study, repeated records of body weight gains on goats were analyzed fitting fixed and random regression models. Up to eight ‘repeated records’ per goat, measured between 10th and 80th day of age post the time of initial body weight recording, were available for analysis.

The objectives of this study were to compare the growth curve of animals in different treatments and to evaluate the differences in body weight gains caused by different rations in the treatments and their implications on choosing a ration.

Results showed that a linear regression on age modelled changes in variation of body weight gain adequately. A ration with E. brucei leaf was found to provide goat with good body weight gain with a minimum cost of ration.

Keywords: Body weight gain; Covariance structure; Feeding trial; Fixed and random regressions; Goat; Model selection