Regresi Nonparametrik Spline Truncated

Nonparametric regression is used to determine the relationship between the response variable and the predictor variable whose shape of the regression curve is not known. This study examines the factors that affect the number of tuberculosis cases in Central Java in 2021. The number of berculosis cases in Central Java reached 117 cases per 115,000 residents with a mean of 110,35 and a variance of 1360.74. Tuberculosis case rates and their affecting factors are modeled using a spline truncated nonparametric regression method. The relationship between tuberculosis case rates in Central Java and the factors that are thought to affect it does not form a specific plot. . Based on the research results, the best model of the minimum Mean Square Error (MSE) value is obtained at the knot point combination (1, 3, 2, 3, 3), with a MSE value of 0.57. The model, it is known that all factors have a significant effect on tuberculosis cases in Central Java, with a coefficient of determination of 93.41%. That is, the model can explain the diversity of tuberculosis cases in Central Java by 93.41%.