Muhammad Rozzaq Hamidi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Muhammad Rozzaq Hamidi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Utriweni Mukhaiyar
Statistics Research Division, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia
2 shared publications - Asrul Irfanullah
1) Doctoral Program of Mathematics, Faculty of Mathematics and Natural Science, Institut Teknologi Bandung, Bandung 40132, Indonesia. 2) Statistics Research Group, Faculty of Mathematics and Natural Science, Institut Teknologi Bandung, Bandung 40132, Indonesia
1 shared publication - Kurnia Novita Sari
Statistics Research Division, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia
1 shared publication - Nuraziza Arfan
Actuarial Master Study Program, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia
1 shared publication - Nurhayati Nurhayati
Doctoral Program in Mathematics, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia
1 shared publication
Latest Publications
- Open Access
- 24 August 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (4) , 3371-3390
SPATIO-TEMPORAL MODELING OF SEMI-HETEROSKEDASTIC RAINFALL DATA USING A GSTAR-GARCH FRAMEWORK
Rainfall often varies across time and space, with sudden and irregular changes that are difficult to capture. These variations are commonly linked to residual heteroskedasticity and spatial dependence, both of which can reduce the accuracy of statistical modeling when ignored. This study considers a semi-heteroskedastic setting, where residuals at one location remain stable while those at another show varying variance. To accommodate this mixed structure, we construct a covariance matrix that reflects both conditions. A hybrid model is then proposed by combining the Generalized Space-Time Autoregressive (GSTAR) framework with the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) process. The GARCH component is used because it generalizes ARCH through a more flexible lag structure, allowing for better representation of volatility persistence and long-term fluctuations. The approach is applied to monthly average rainfall data retrieved from the NASA POWER database for two sites in Tasikmalaya Regency, Indonesia, which differ in distributional patterns and variability. The results show that the GSTAR-GARCH model can effectively capture spatial and temporal dependencies as well as volatility dynamics, performing consistently in both estimation and validation stages.
- 24 August 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (4) , 3371-3390
Open AccessSPATIO-TEMPORAL MODELING OF SEMI-HETEROSKEDASTIC RAINFALL DATA USING A GSTAR-GARCH FRAMEWORK
Rainfall often varies across time and space, with sudden and irregular changes that are difficult to capture. These variations are commonly linked to residual heteroskedasticity and spatial dependence, both of which can reduce the accuracy of statistical modeling when ignored. This study considers a semi-heteroskedastic setting, where residuals at one location remain stable while those at another show varying variance. To accommodate this mixed structure, we construct a covariance matrix that reflects both conditions. A hybrid model is then proposed by combining the Generalized Space-Time Autoregressive (GSTAR) framework with the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) process. The GARCH component is used because it generalizes ARCH through a more flexible lag structure, allowing for better representation of volatility persistence and long-term fluctuations. The approach is applied to monthly average rainfall data retrieved from the NASA POWER database for two sites in Tasikmalaya Regency, Indonesia, which differ in distributional patterns and variability. The results show that the GSTAR-GARCH model can effectively capture spatial and temporal dependencies as well as volatility dynamics, performing consistently in both estimation and validation stages.
- Open Access
- 13 January 2025
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 19 (1) , 629-642
COMPARISON OF SURVIVAL ANALYSIS USING ACCELERATED FAILURE TIME MODEL AND COX MODEL FOR RECIDIVIST CASE
Recidivists, or ex-prisoners who commit crimes after serving a prior sentence, pose a critical challenge to the criminal justice system. This study examines social and economic factors that may reduce the likelihood of recidivists being re-arrested. Using survival analysis, the probability that a recidivist could survive in society without being re-arrested could be estimated. The purpose of this work is to compare the AFT and Cox models to determine which provides a better fit to identify factors affecting the likelihood of re-arrest within one year after release and to statistically assess the impact of these factors. This study utilizes a stratified Cox model to address variables that violate the proportional hazards (PH) assumption. The analysis is limited to four types of AFT models: Weibull, log-normal, log-logistic, and exponential. Results show that the stratified Cox model provides the best fit, based on Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). This demonstrates the Cox model's robustness in analyzing survival data, accurately approximating the distribution of survival times without restrictive assumptions, unlike AFT models. The study reveals that recidivists who received financial aid upon release have a lower risk of re-arrest compared to those who did not, and each additional prior theft arrest increased the risk of re-arrest by 1.09193 times.
- 13 January 2025
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 19 (1) , 629-642
Open AccessCOMPARISON OF SURVIVAL ANALYSIS USING ACCELERATED FAILURE TIME MODEL AND COX MODEL FOR RECIDIVIST CASE
Recidivists, or ex-prisoners who commit crimes after serving a prior sentence, pose a critical challenge to the criminal justice system. This study examines social and economic factors that may reduce the likelihood of recidivists being re-arrested. Using survival analysis, the probability that a recidivist could survive in society without being re-arrested could be estimated. The purpose of this work is to compare the AFT and Cox models to determine which provides a better fit to identify factors affecting the likelihood of re-arrest within one year after release and to statistically assess the impact of these factors. This study utilizes a stratified Cox model to address variables that violate the proportional hazards (PH) assumption. The analysis is limited to four types of AFT models: Weibull, log-normal, log-logistic, and exponential. Results show that the stratified Cox model provides the best fit, based on Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). This demonstrates the Cox model's robustness in analyzing survival data, accurately approximating the distribution of survival times without restrictive assumptions, unlike AFT models. The study reveals that recidivists who received financial aid upon release have a lower risk of re-arrest compared to those who did not, and each additional prior theft arrest increased the risk of re-arrest by 1.09193 times.