A Semiparametric Regression for Modelling Life Expectancy: Spline Truncated and Fourier Series Estimators

DOI

10.2991/978-2-38476-481-5_18How to use a DOI?

Keywords

Semiparametric; Truncated Spline; Fourier Series; Life Expectancy

Abstract

Regression approaches were categorized into parametric, nonparametric, and semiparametric. Parametric regression models required assumptions about the form of the relationship function, as seen in simple linear regression. Whereas, nonparametric regression models did not require specific assumptions, making them more flexible in capturing complex and non-linear patterns. When the relationship between variables was not entirely linear or non-linear, the semiparametric approach was used, combining parametric and nonparametric components to improve model accuracy. This study modeled the life expectancy (LE) in East Java Province for the year 2022 using a semiparametric regression approach that combined truncated spline and Fourier series estimators. This approach integrated a parametric linear model for the literacy rate, and nonparametric models: a truncated spline for the labor force participation rate variable, and Fourier series for the infant mortality rate, percentage of young children (ages 0–23 months) receiving breastfeeding, and average years of schooling. The choice of knots in the truncated spline was determined based on the range of average years of schooling values. Fourier series were used to capture periodic patterns. With different oscillation variations for each variable. The optimal model combination included one truncated spline component and three Fourier series components. The research results showed that the GCV value obtained from the model was 2.899. And the MSE value was 1.2519. The coefficient of determination obtained was 85.66%, indicating that this model was able to explain a substantial portion of the variability. And the semiparametric approach better captured the complexity of the data.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Firda Fadri
AU  - Kiswara Agung Santoso
AU  - Sandya Nur Indrawati Karsan
PY  - 2025
DA  - 2025/11/19
TI  - A Semiparametric Regression for Modelling Life Expectancy: Spline Truncated and Fourier Series Estimators
BT  - Proceedings of the 9th International Conference on Research, Implementation, and Education of Mathematics and Sciences (ICRIEMS 2022)
PB  - Atlantis Press
SP  - 182
EP  - 190
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-481-5_18
DO  - 10.2991/978-2-38476-481-5_18
ID  - Fadri2025
ER  -