Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal ILMU KELAUTAN: Indonesian Journal of Marine Sciences Communication in Biomathematical Sciences
Izzaturrahim, Muh. Hafizh
Unknown Affiliation
Earth & Planetary Sciences Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Communication in Biomathematical Sciences

 1 
Regresi Multiskala Tertimbang Geografis dan Temporal dengan LASSO dan Adaptif LASSO untuk Pemetaan Kejadian Tuberkulosis di Jawa Barat Habsy, Muhammad Yusuf Al; Rachmawati, Ro'fah Nur; Khotimah, Purnomo Husnul; Natari, Rifani Bhakti; Riswantini, Dianadewi; Munandar, Devi; Izzaturrahim, Muh. Hafizh
Communication in Biomathematical Sciences Vol. 8 No. 1 (2025)
Publisher : The Indonesian Bio-Mathematical Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/cbms.2025.8.1.6

Abstract

Tuberculosis (TB) is a global health issue caused by Mycobacterium tuberculosis and can affect any organ of the body, especially the lungs. The trend of TB cases varies between regions, and analytic assessment is required to identify the predictor variables. The purpose of this research is to compare the Multiscale Geographically and Temporally Weighted Regression (MGTWR) and the Geographically and Temporally Weighted Regression (GTWR) method, which both use Gaussian, Exponential, Uniform, and Bi-Square kernel functions, to identify significant variables in each region annually. The MGTWR method has the advantage of using a flexible bandwidth for each observation, that results in more accurate coefficient estimates. The sample used was 27 districts and cities in West Java Province, involving 36 variables divided into 5 dimensions, namely global climate, health, demography, population, and government policy, with a time span of 2019–2022. To overcome the problem of multicollinearity, the approach was carried out using the Least Absolute Shrinkage Selection Operator (LASSO) and Adaptive LASSO methods. In determining the best model, the prioritized criteria are to achieve the highest R2, which indicates the optimal level of model fit, as well as the smallest AIC, which indicates the most efficient model goodness of fit. The best model is MGTWR with LASSO variable selection on the Bi-Square kernel. This model has an R2 of 91.25% and the smallest AIC of 139.868. From the best model, each region emerged with a cluster structure affected by various variables from 2019 to 2022, providing an in-depth understanding of TB mapping that can assist in formulating more effective intervention measures.
Co-Authors Devi Munandar, Devi Habsy, Muhammad Yusuf Al Hatmaja, Rahaden Bagas Herlina Ika Ratnawati, Herlina Ika Heryoso Setiyono Khotimah, Purnomo Husnul Latifah, Laila Lelalette, Johanis Dominggus M. Furqon Azis Ismail Mario Putra Suhana Muhammad Helmi Natari, Rifani Bhakti Rachmawati, Ro'fah Nur Riswantini, Dianadewi Ryanto, Fauzan Novan Setiyadi, Johar Subekti Mujiasih Widodo S Pranowo