Platelet Modeling Based On Hematocrit in DHF Patients with Spline Quantile Regression

Quantile nonparametric regression is used to estimate the regression function when assumptions about the shape of the regression curve are unknown. It is only assumed to be smooth by involving quantile values. One estimator in nonparametric regression is spline. The segmented properties of the spline provide more flexibility than ordinary polynomials. Therefore, the nature of the spline makes it possible to adapt more effectively to the local characteristics of a function or data. This study makes a model for platelet counts based on hematocrit of Dengue Hemorrhagic Fever patients with linear spline quantile regression. The optimal model obtained from the estimation of linear spline quantile regression is at quantile 0.5 with two knots and the GCV value is 40,799. Based on the model, there are three segments of platelet change based on hematocrit. There is a decreased platelet segment with increasing percentage of hematocrit. However, there is a hematocrit segment of 36.9-46.9 which should receive attention where platelets increase in that interval.