MULTIRESPONSE REGRESSION SEMIPARAMETRIC TRUNCATED SPLINE (CASE STUDY: SKIN DEFECT OF FARMING COWS)

This study aims to model a semiparametric multiresponse regression analysis model using the Truncated Spline approach as a solution in its nonparametric component to obtain the best model in the case study to help prevent and treat skin diseases in cattle. The solution is done using Weighted Least Square (WLS) to be able to capture multiresponse modeling where there are indications between parts of the same cow's body that have correlated wounds. The novelty of this research is on a semiparametric truncated spline multiresponse model using a non-uniform order and number of knots for each predictor variables.