PENDEKATAN REGRESI SPLINE UNTUK MEMODELKAN POLA PERTUMBUHAN BERAT BADAN BALITA

• Main Authors: NI LUH SUKERNI, I KOMANG GDE SUKARSA, NI LUH PUTU SUCIPTAWATI
• Format: Article
• Language: English
• Published: Universitas Udayana 2018-09-01
• Series: E-Jurnal Matematika
• Online Access: https://ojs.unud.ac.id/index.php/mtk/article/view/41903

The study is aimed to estimate the best spline regression model for toddler’s weight growth patterns. Spline is one of the nonparametric regression estimation method which has a high flexibility and is able to handle data that change in particular subintervals so thus resulting in model which fitted the data. This study uses data of toddler’s weight growth at Posyandu Mekar Sari, Desa Suwug, Kabupaten Buleleng. The best spline regression model is chosen based on the minimum Generalized Cross Validation (GCV) value. The study shows that the best spline regression model for the data is quadratic spline regression model with six optimal knot points. The minimum GCV value is 0,900683471925 with the determination coefficient  equals to 0,954609.