Pemodelan Jumlah Kasus Tuberkulosis Di Provinsi Jawa Tengah Menggunakan Geographically Weighted Negative Binomial Regression

Firdianto, Dafa Rifqi (2024) Pemodelan Jumlah Kasus Tuberkulosis Di Provinsi Jawa Tengah Menggunakan Geographically Weighted Negative Binomial Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211060-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Infeksi bakteri Mycobacterium Tuberculosis di paru menyebabkan Tuberkulosis (TBC). TBC menjadi penyebab kematian kedua terbesar di dunia dari satu agen infeksi, setelah penyakit virus corona (COVID-19). Provinsi Jawa Tengah hanya mencapai cakupan penemuan Tuberkulosis Resistan Obat (TBC RO) 46% dari target nasional sebesar 70%. Jumlah kasus Tuberkulosis merupakan data diskrit yang sering kali terjadi overdispersi sehingga dapat diananlisis menggunakan Geographically Weighted Negative Binomial Regression (GWNBR).
Hasil analisis menunjukkan karakteristik jumlah kasus TBC beserta faktor-faktor yang memengaruhinya memiliki pola yang variatif pada tiap kabupaten/kota. Terdapat kasus overdispersi pada data atau varians lebih besar dari rata-rata sehingga dilanjutkan ke Regresi Binomial Negatif. Kemudian, pada pengujian aspek spasial terdapat dependensi spasial dan heterogenitas spasial sehingga dapat analisis menggunakan GWNBR. Pembobot optimum yang terpilih adalah Fix Gaussian Kernel karena memiliki nilai Akaike Information Criterion (AIC) terkecil apabila dibandingkan pembobot lain. Pengelompokan kabupaten/kota di Jawa Tengah berdasarkan variabel signifikan yang sama menghasilkan 5 kelompok-Kelompok dengan variabel signifikan yang sedikit akan mempermudah penanganan karena pemerintah bisa lebih fokus pada faktor tersebut. Pemodelan GWNBR menghasilkan 3 variabel yang berpengaruh signifikan terhadap jumlah kasus TBC di semua kabupaten/kota di Provinsi Jawa Tengah, yaitu
kepadatan penduduk (X1), jumlah tenaga medis (X4), dan rata-rata lama sekolah (X7).
=======================================================================================================================================
Mycobacterium tuberculosis bacterial infection in the lungs causes Tuberculosis (TB). Tuberculosis is the world's second-largest cause of death from a single infectious agent, after coronavirus disease (COVID-19). Central Java Province has only achieved the coverage of the discovery of 46% of the national target of 70% of the drug-resistant tuberculosis (RO TB). The number of Tuberculosis cases is discrete data that often occurs overdispersion so that it can be analyzed using Geographically Weighted Negative Binomial Regression (GWNBR). The results of the analysis show that the characteristics of the number of TB cases and the factors that affect them have a varied pattern in each district/city. There are cases of overdispersion in the data or variance greater than the average so that it continues to Negative Binomial Regression. Then, in the spatial aspect test, there are spatial dependencies and spatial heterogeneity so that they can be analyzed using GWNBR. The optimal weighting chosen is Fix Gaussian Kernel because it has the smallest Akaike Information Criterion (AIC) value when compared to other weights. The grouping of districts/cities in Central Java based on the same
significant variable resulted in 5 groups. Groups with few significant variables will make it easier to handle because the government can focus more on these factors. GWNBR modeling produced 3 variables that had a significant effect on the number of TB cases in all districts/cities
in Central Java Province, namely population density (X1), number of medical personnel (X4),
and average length of school (X7).

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Central Java, GWNBR, Negative Binomial Regression, Tuberculosis, GWNBR, Jawa Tengah, Regresi Binomial Negatif, Tuberkulosis
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis.
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Dafa Rifqi Firdianto
Date Deposited:	14 Jul 2025 00:41
Last Modified:	14 Jul 2025 00:41
URI:	http://repository.its.ac.id/id/eprint/119552

Actions (login required)

View Item