Geographically And Temporally Weighted Bivariate Generalized Poisson Regression Model (Studi Kasus: Pemodelan Penambahan Kasus Covid-19 dan Penambahan Kematian Akibat Covid-19 di Provinsi Jawa Timur)

Purwanti, Setyorini Indah (2021) Geographically And Temporally Weighted Bivariate Generalized Poisson Regression Model (Studi Kasus: Pemodelan Penambahan Kasus Covid-19 dan Penambahan Kematian Akibat Covid-19 di Provinsi Jawa Timur). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 06211950017005-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (4MB) | Request a copy

Abstract

Bivariate Generalized Poisson Regression (BGPR) merupakan salah satu alternatif untuk memodelkan data cacahan (count) dengan dua respon yang saling berkorelasi dan terjadi overdispersi atau underdispersi. Pada data panel dengan unit observasi berupa wilayah, penggunaan BGPR kurang tepat karena pada data tersebut terdapat heterogenitas spasial dan temporal. Geographically and Temporally Weighted Bivariate Generalized Poisson Regression (GTWBGPR) merupakan metode untuk memodelkan data dengan heterogenitas spasial dan temporal. GTWBGPR merupakan pengembangan dari Geographically Weighted Bivariate Generalized Poisson Regression (GWBGPR). Pada GTWBGPR, selain mengakomodasi efek spasial, juga mengakomodasi efek temporal. Pada penelitian ini membahas estimasi parameter dan statistik uji untuk model GTWBGPR. Estimasi parameter menggunakan Maximum Likelihood Estimation (MLE), namun hasilnya tidak closed-form sehingga diselesaikan dengan iterasi numerik. Iterasi numerik yang digunakan adalah Newton Raphson. Statistik uji untuk pengujian serentak menggunakan Maximum Likelihood Ratio Test (MLRT). Selanjutnya model diaplikasikan pada pemodelan penambahan kasus covid-19 dan penambahan kematian akibat covid-19 di Jawa Timur. Pemodelan menggunakan GTWBGPR pada periode pertama hingga ketiga menghasilkan 5 kelompok kabupaten/kota berdasarkan variabel yang signifikan terhadap penambahan kasus covid-19 dan 4 kelompok kabupaten/kota berdasarkan variabel yang signifikan terhadap penambahan kematian akibat covid-19. Pada periode keempat dan kelima, semua variabel prediktor berpengaruh signifikan terhadap kedua respon, yaitu rata-rata suhu, rata-rata kelembaban, dan rasio pemeriksaan spesimen per 100.000 penduduk.
======================================================================================================
Bivariate Generalized Poisson Regression (BGPR) is an alternative for modeling count data with two correlated responses and overdispersion or underdispersion occurs. However, in panel data with an observation unit in the form of an area, the use of BGPR is not appropriate because the data contains spatial and temporal heterogeneity. Geographically and Temporally Weighted Bivariate Generalized Poisson Regression (GTWBGPR) is a method for modeling data with spatial and temporal heterogeneity. GTWBGPR is an extension of Geographically Weighted Bivariate Generalized Poisson Regression (GWBGPR). In GTWBGPR, apart from accommodating spatial effects, it also accommodates temporal effects. This study discusses parameter estimation and test statistics for the GTWBGPR model. Parameter estimation using Maximum Likelihood Estimation (MLE), but the result is not closed-form so it is solved by numerical iteration. The numerical iteration used is Newton Raphson. Test statistics for simultaneous testing using the Maximum Likelihood Ratio Test (MLRT). Furthermore, the model was applied to modeling the addition of COVID-19 cases and the addition of deaths due to COVID-19 in East Java. Modeling using GTWBGPR in the first to third period resulted in 5 groups of districts/cities based on variables that were significant for the addition of COVID-19 cases and 4 groups of districts/cities based on variables that were significant for the addition of deaths due to COVID-19. While in the fourth and fifth periods, all predictor variables had a significant effect on both responses, namely the average temperature, the average humidity, and the ratio of specimen examination per 100,000 population.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	GTWBGPR, Kasus Covid-19, Kematian Akibat Covid-19, MLE, MLRT, Covid-19 Cases, Deaths Due to Covid-19, GTWBGPR, MLE, MLRT.
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA371 Differential equations--Numerical solutions
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis
Depositing User:	Setyorini Indah Purwanti
Date Deposited:	10 Sep 2021 11:34
Last Modified:	10 Sep 2021 11:34
URI:	http://repository.its.ac.id/id/eprint/91962

Actions (login required)

View Item