ESTIMATES OF DIRECT AND MATERNAL (CO)VARIANCE COMPONENTS OF GROWTH TRAITS IN BORAN CATTLE

Birth (BW), weaning (WW) and yearling weight (YW) data of Boran cattle from Abernossa ranch of the Ministry of Agriculture of Ethiopia were analysed to estimate genetic parameters due to maternal and direct effects. In the univariate analysis, six different models ranging from 'simple' animal model (model 1) to a model which included direct and maternal genetic effects and their correlation, and permanent environmental effects (model 6), were applied. After comparing the log likelihood values, model 4, which included direct and maternal genetic effect and their correlation for BW, and model 6 for WW and YW, were selected to be appropriate. For BW, a direct heritability (h(d)2) of 0.24 and a maternal heritability (h(m)2) of 0.08 were estimated. In the case of WW and YW, the estimates were 0.29 and 0.34 for h(d)2 and 0.06 and 0.05 for h(m)2, respectively. The ratio of permanent environmental variance to the total (c2) was 0.14 and 0.05 for WW and YW, respectively. Estimates from the bivariate and trivariate analyses were similar to those from univariate analysis but the estimates for h(d)2 were relatively higher. In particular, parameter estimates of WW and YW together, as well as the trivariate analysis, appeared to have accounted for selection bias on WW and thus resulted in a higher h(d)2 estimate for YW. The across-trait correlation estimates were low to medium with the expception of high direct genetic and permanent environmental correlations between WW and YW. Generally, parameter estimates of Boran cattle were within the range of those for other breeds. However, the genetic antagonism between direct and maternal effects seems to be stronger (-0.33 to -0.68).