ANALYSIS OF FACTORS AFFECTING PNEUMONIA IN INDONESIAN TODDLERS USING NONPARAMETRIC REGRESSION WITH LEAST SQUARE SPLINE AND FOURIER SERIES METHODS

Pneumonia is the leading cause of death among children under five, with the highest prevalence in Indonesia found in West Papua Province (75%) and the lowest in North Sulawesi (0.3%). This study aims to analyze the factors influencing the prevalence of pneumonia in Indonesian toddlers using nonparametric regression approach by comparing Least Square Spline (LS-Spline) and Fourier Series. Data sourced from the Indonesian Ministry of Health website, consisting of 34 provinces in Indonesia in 2023, with one response variable (Y) and five predictor variables (X). The analyzed factors include the coverage of vitamin A supplementation, malnutrition rates, low birth weight prevalence, measles immunization coverage, and exclusive breastfeeding rates. The analysis was conducted by modeling with nonparametric Least Square Spline regression using up to three optimal knot points, then performing analysis using nonparametric regression with the Fourier series approach. The two methods were compared based on GCV and R², with the best model having lower GCV and higher R². The results showed that LS-Spline was better than Fourier Series, with a GCV value of 233.16 and a coefficient of determination of 92.5%. The findings reveal that the relationships between predictor factors and pneumonia prevalence are nonlinear, with varying influence patterns across different variable ranges. These results indicate that LS-Spline has a strong ability to explain data variability. The Fourier series is limited in this study because it is best suited for periodic data, unlike pneumonia data and its causal factors which do not show such patterns. The weakness of the Fourier Series in this study lies in its suitability for periodic data, while pneumonia cases and their causal factors do not follow such patterns. This study offers insights into health policy making to reduce pneumonia cases, improve their lives, in line with the SDGs target on Good Health and Well-being.

Authors

Institutions

Publication Details

Journal
BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN
Published
2025-11-24
DOI
https://doi.org/10.30598/barekengvol20iss1pp0087-0104
Primary Topic
Statistical Methods in Epidemiology
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ANALYSIS OF FACTORS AFFECTING PNEUMONIA IN INDONESIAN TODDLERS USING NONPARAMETRIC REGRESSION WITH LEAST SQUARE SPLINE AND FOURIER SERIES METHODS

Suliyanto Suliyanto, Toha Saifudin, Mohammad Noufal Ubadah, Sabrina Salsa Oktavia et al.
BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN
Statistical Methods in Epidemiology
article

ANALYSIS OF FACTORS AFFECTING PNEUMONIA IN INDONESIAN TODDLERS USING NONPARAMETRIC REGRESSION WITH LEAST SQUARE SPLINE AND FOURIER SERIES METHODS

Suliyanto Suliyanto, Toha Saifudin, Mohammad Noufal Ubadah, Sabrina Salsa Oktavia, Jovansha Ariyawan, Nabila Nurdin, Bryan Given Christiano Ginzel
article en

Abstract

Pneumonia is the leading cause of death among children under five, with the highest prevalence in Indonesia found in West Papua Province (75%) and the lowest in North Sulawesi (0.3%). This study aims to analyze the factors influencing the prevalence of pneumonia in Indonesian toddlers using nonparametric regression approach by comparing Least Square Spline (LS-Spline) and Fourier Series. Data sourced from the Indonesian Ministry of Health website, consisting of 34 provinces in Indonesia in 2023, with one response variable (Y) and five predictor variables (X). The analyzed factors include the coverage of vitamin A supplementation, malnutrition rates, low birth weight prevalence, measles immunization coverage, and exclusive breastfeeding rates. The analysis was conducted by modeling with nonparametric Least Square Spline regression using up to three optimal knot points, then performing analysis using nonparametric regression with the Fourier series approach. The two methods were compared based on GCV and R², with the best model having lower GCV and higher R². The results showed that LS-Spline was better than Fourier Series, with a GCV value of 233.16 and a coefficient of determination of 92.5%. The findings reveal that the relationships between predictor factors and pneumonia prevalence are nonlinear, with varying influence patterns across different variable ranges. These results indicate that LS-Spline has a strong ability to explain data variability. The Fourier series is limited in this study because it is best suited for periodic data, unlike pneumonia data and its causal factors which do not show such patterns. The weakness of the Fourier Series in this study lies in its suitability for periodic data, while pneumonia cases and their causal factors do not follow such patterns. This study offers insights into health policy making to reduce pneumonia cases, improve their lives, in line with the SDGs target on Good Health and Well-being.

BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPANVol. 20(1)
Universitas Airlangga (ID)
Ministry of Health of the Republic of Indonesia
Openalex Percentile: Top 66%
Statistical Methods in Epidemiology
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.