Pemodelan Kejadian Bayi Berat Badan Lahir Rendah Di Kota Surabaya Dengan Metode Generalized Poisson Spatial Autoregressive

Epiphani, Nathania Grace (2026) Pemodelan Kejadian Bayi Berat Badan Lahir Rendah Di Kota Surabaya Dengan Metode Generalized Poisson Spatial Autoregressive. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003221070-Undergraduate-Thesis.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Bayi berat badan lahir rendah (BBLR) merupakan kondisi bayi yang lahir dengan berat badan kurang dari 2.500 gram dalam 24 jam pertama setelah kelahiran. BBLR menjadi perhatian penting dalam kesehatan masyarakat karena berhubungan dengan peningkatan risiko kematian neonatal, stunting, serta berbagai penyakit tidak menular pada usia dewasa. Kejadian BBLR yang berbentuk data count dan dipengaruhi oleh karakteristik ibu serta kondisi lingkungan yang berbeda antarwilayah berpotensi mengalami overdispersi dan dependensi spasial. Oleh karena itu, dilakukan pemodelan kejadian BBLR menggunakan metode Generalized Poisson Spatial Autoregressive (GPSAR) dengan jumlah bayi lahir hidup sebagai variabel exposure. Hasil analisis menunjukkan bahwa data BBLR mengalami overdispersi dan memiliki dependensi spasial positif yang ditunjukkan oleh nilai positif pada Indeks Moran's I. Hasil perbandingan model menunjukkan bahwa model GPSAR memiliki kinerja yang lebih baik daripada model Generalized Poisson Regression (GPR). Keunggulan tersebut ditunjukkan oleh nilai Akaike’s Information Criterion Corrected (AICc) sebesar 457,45 pada GPSAR dan 475,00 pada GPR. Model GPSAR menghasilkan kesimpulan variabel bayi prematur, ibu hamil dengan anemia, dan rumah tangga dengan akses sanitasi layak sendiri berpengaruh signifikan terhadap angka kejadian BBLR di puskesmas Kota Surabaya.
=======================================================================================================================================
Low Birth Weight (LBW) is a condition in which a baby is born weighing less than 2,500 grams within the first 24 hours after birth. LBW has become a crucial public health concern because it is associated with an increased risk of neonatal mortality, stunting, and various non-communicable diseases in adulthood. LBW incidence, which constitutes count data and is influenced by maternal characteristics and environmental conditions that vary across regions, has the potential to experience overdispersion and spatial dependency. Therefore, the modeling of LBW incidence was conducted using the Generalized Poisson Spatial Autoregressive (GPSAR) method, with the number of live births as the exposure variable. The analysis results show that the LBW data experiences overdispersion and has a positive spatial dependency, as indicated by a positive Moran's I Index. The model comparison results show that the Generalized Poisson Spatial Autoregressive (GPSAR) model performs better than the Generalized Poisson Regression (GPR) model. This superiority is indicated by the lower Akaike’s Information Criterion Corrected (AICc) value of 457.45 for the GPSAR model, compared with 475.00 for the GPR model. The GPSAR model concludes that the variables of premature babies, pregnant women with anemia, and households with their own access to proper sanitation significantly affect the incidence rate of LBW across community health centers in Surabaya City.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	BBLR, Exposure, Generalized Poisson Spatial Autoregressive, Spasial, Surabaya, LBW, Exposure, Generalized Poisson Spatial Autoregressive, Spatial, Surabaya
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Nathania Grace Epiphani
Date Deposited:	03 Aug 2026 09:21
Last Modified:	03 Aug 2026 09:21
URI:	http://repository.its.ac.id/id/eprint/141408

Actions (login required)

View Item