Estimasi Paramater Pada Model Case-Control Point Process (Studi Kasus: Analisis Faktor Spasial Terhadap Risiko Kematian Akibat Covid-19 Di Surabaya)

Putri, Dora Isnaini (2022) Estimasi Paramater Pada Model Case-Control Point Process (Studi Kasus: Analisis Faktor Spasial Terhadap Risiko Kematian Akibat Covid-19 Di Surabaya). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6003201015_Master_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

COVID-19 merupakan salah satu penyakit menular yang disebabkan oleh jenis Coronavirus. Pasien yang terkena COVID-19 dapat mengalami gejala ringan hingga kematian. Kasus kematian akibat COVID-19 cukup tinggi, terutama di Surabaya sebagai episenter Provinsi Jawa Timur. Spatial point pattern pada kejadian COVID-19 yang berupa koordinat lintang dan bujur dari alamat pasien COVID-19 dapat digunakan sebagai analisis untuk mengetahui faktor spasial kematian akibat COVID-19. Penggunaan case-control methodology dapat digunakan untuk menganalisis peluang terjadinya kematian dari banyaknya pasien yang terpapar COVID-19 dan mengetahui faktor spasial terhadap risiko kematian akibat COVID-19, jika digabungkan dengan spatial point pattern dari data pasien COVID-19 maka akan membentuk case-control point process. Kasus merupakan pasien COVID-19 yang meninggal dunia, dan kontrol adalah pasien terkonfirmasi positif COVID-19 di Surabaya. Penggunaan data kovariat seperti proporsi usia pasien diatas 60 tahun, dan kepadatan rumah sakit serta proporsi banyaknya rumah sakit per kecamatan menjadi faktor pendukung dalam menganalisis risiko spasial kematian akibat COVID-19. Parameter model case-control point process dapat diestimasi dengan menggunakan Maximum Likelihood Estimation (MLE). Proses estimasi dilanjutkan dengan metode iterasi numerik Iteratively Reweighted Least Square (IRLS) menggunakan ekspansi Taylor. Hasil pemodelan case-control point process pada data COVID-19 di Surabaya, didapatkan bahwa model dengan covariate proporsi usia dan proporsi rumah sakit merupakan model terbaik dengan nilai BIC terendah, dan menunjukkan bahwa covariate pada penelitian ini tidak memberikan pengaruh terhadap kematian akibat COVID-19 di Surabaya. Peluang terjadinya kematian akibat COVID-19 meningkat seiring dengan banyaknya pasien yang terpapar COVID-19.
====================================================================================================================================
COVID-19 is an infectious disease caused by a type of Coronavirus. Patients with COVID-19 can experience mild symptoms to death. Cases of death due to COVID-19 are quite high, especially in Surabaya as the epicenter of East Java Province. The spatial point pattern in the COVID-19 incident in the form of latitude and longitude coordinates from the address of a COVID-19 patient can be used as an analysis to determine the spatial factors of death due to COVID-19. The use of case-control methodology can be used to analyze the probability of death from the number of patients exposed to COVID-19 and determine the spatial factors on the risk of death from COVID-19, when combined with the spatial point pattern from the data of COVID-19 patients, it will form a case-control point process. Cases are COVID-19 patients who died, and controls are patients who have been confirmed positive for COVID-19 in Surabaya. The use of covariate data such as the proportion of patients aged over 60 years, and hospital density and the proportion of hospitals per sub-district are supporting factors in analyzing the spatial risk of death due to COVID-19. The case-control point process model parameters can be estimated using Maximum Likelihood Estimation (MLE). The estimation process is continued with the Iteratively Reweighted Least Square (IRLS) numerical iteration method using Taylor expansion. The results of the case-control point process modeling on COVID-19 data in Surabaya, it was found that the model with the covariate proportion of age and proportion of hospital was the best model with the lowest BIC value, and showed that the covariate in this study had no effect on mortality from COVID-19 in Surabaya. The chance of dying from COVID-19 increases with the number of patients exposed to COVID-19.

Item Type:	Thesis (Masters)
Additional Information:	RTSt 519.544 Put e-1 2022
Uncontrolled Keywords:	Case-control point process, COVID-19, Poisson point process, Spatial point pattern, Spatial point process.
Subjects:	H Social Sciences > HA Statistics > HA31.7 Estimation
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	29 Apr 2026 08:31
Last Modified:	29 Apr 2026 08:31
URI:	http://repository.its.ac.id/id/eprint/132937

Actions (login required)

View Item