The use of the binary spline logistic regression model on the nutritional status data of children

Abstract

The nutritional status of children can be grouped into two, namely normal and abnormal nutrition so that the data are analyzed using a binary logistic regression model. In this study, the use of binary logistic regression was developed on the use of the spline estimator as part of the nonparametric regression approach. This model is able to model qualitative response data by showing several trends that may occur in the data. Data on the nutritional status of children were analyzed based on the child's weight through a linear spline estimator and the optimal model was obtained at the use of a one-knot point, which was 4.7 kg. These results indicate that if a child has a body weight of 4.7 kg and above then there is a chance that the child has an abnormal nutritional status of 9.013 times compared to a child with a body weight below 4.7 kg. This could be due to the fact that children are no longer getting breast milk, so they need to get attention regarding their nutritional status.