Analyzing Low Birthweight in Java Based on Logistic Regression Model for Matched Pair Data: Analisis Berat Badan Lahir Rendah di Pulau Jawa Berdasarkan Model Regresi Logistik untuk Data Berpadanan

Christiana Anggraeni Putri (Department of Statistics, IPB University, Indonesia)
Rini Irfani (Department of Statistics, IPB University, Indonesia)
Khairil Anwar Notodiputro (Department of Statistics, IPB University, Indonesia)

Indonesian Journal of Statistics and Its Applications
Vol 7 No 2 (2023)

Low birthweight is one of the leading causes of neonatal death. Generally, the study of low birth weight is done by modeling logistic regression without considering the influence of confounding variables that can deviate the actual relationship between the explanatory variables and the response. This paper aims to identify low birth weight determinants in Java based on the logistic regression model for conditional study design, in which the analysis is based on matching the education level of the mother with one control. The results of the analysis showed that matched logistic regression can be used to correct bias due to the influence of a confounding variable. It reveals that based on the results of modeling, the frequency of pregnancy examinations and the parity of children are significantly affect the risk of low birth weight in Java Island.