cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Soraya
Contact Email
jurnal.varian@stmikbumigora.ac.id
Phone
+6282339979545
Journal Mail Official
jurnal.varian@stmikbumigora.ac.id
Editorial Address
Jln. Ismail Marzuki - Cilinaya - Cakranegara - Mataram 83127
Location
Kota mataram,
Nusa tenggara barat
INDONESIA
Jurnal Varian
Published by Universitas Bumigora
ISSN : -     EISSN : 25812017     DOI : https://doi.org/10.30812/varian
Core Subject : Economy, Science, Education, Social,
Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Mathematics Social Sciences Other
Jurnal Varian adalah salah satu Jurnal Ilmiah yang terdapat di Universitas Bumigora. Jurnal ini bertujuan untuk memberikan wadah atau sarana publikasi bagi para dosen, peneliti dan praktisi baik di lingkungan internal maupun eksternal Universitas Bumigora Mataram. Jurnal ini terbit 2 (dua) kali dalam 1 tahun pada periode Genap (April) dan Ganjil (Oktober). Jurnal Varian fokus memuat publikasi pada Bidang Matematika dan Statistika.
Arjuna Subject : Matematika - Statistik dan Probabilitas
Articles 198 Documents
 16   17   18   19   20 
Water, Sanitation, and Under-Five Mortality: A Regularized Panel Machine Learning Approach Selvi Annisa; Fuad Muhajirin Farid; Yeni Rahkmawati; Naomi Nessyana Debataraja
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6355

Abstract

Under-five mortality remains a critical indicator of public health performance, reflecting a country’s socio-environmental progress and overall quality of life. However, studies examining the relationship between basic drinking water, sanitation, and under-five mortality in Southeast Asia remain limited, particularly those that integrate panel data with regularized machine learning to address multicollinearity among development indicators. The objective of this study is to analyze the association between basic drinking water access, basic sanitation access, and under-five mortality across 11 Southeast Asian countries from 2003 to 2023, while controlling for GDP per capita, health expenditure, urban population, and DPT immunization. The method used in this study is a balanced panel data approach combined with regularized regression models, including Ridge Regression, LASSO, and Elastic Net. A conventional panel model is selected through panel specification tests, while regularized models are evaluated using nested cross-validation, with Leave-One-Country-Out Cross-Validation in the outer loop and internal 10-fold cross-validation for parameter tuning. Bootstrap inference is applied to the selected regularized model. The novelty of this study lies in the integration of panel data, regularized machine learning, cross-country validation, and bootstrap inference in under-five mortality modeling. The results show that Ridge Regression achieves the best performance, with an RMSE of 0.4037, MAE of 0.3360, and R² of 0.8193. Basic sanitation access, GDP per capita, urban population, and DPT immunization are negatively associated with under-five mortality. These findings imply that reducing under-five mortality requires integrated policies that improve sanitation, expand immunization, strengthen the economy, and ensure equitable access to basic services.
Comparison of DBSCAN and HDBSCAN Using DBCV for Clustering Flood-Prone Areas Tresna Restu Aufi; Wiwit Pura Nurmayanti; Sifriyani Sifriyani
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6356

Abstract

Floods rank among the most common natural disasters occurring in Indonesia, especially Kalimantan Island, where all regencies/cities experienced floods in 2025. Floods are influenced by complex interactions between natural and human factors and require robust clustering methods such as DBSCAN and HDBSCAN to handle noise. In density-based clustering, core points are dense observations satisfying the minimum neighborhood requirement, boundary points are observations near cluster edges, and noise points are isolated observations not assigned to any cluster. The objective of this study is to compare the performance of DBSCAN and HDBSCAN for clustering flood-prone areas on the island of Kalimantan based on DBCV values. The method used in this study is parameter optimization using DBCV between the DBSCAN and HDBSCAN algorithms on 2025 Village Potential (PODES) data from BPS, covering 56 regencies/cities across five provinces on the island of Kalimantan. Six variables were analyzed: flood, water pollution, river/drainage maintenance, forest/land fires, deforestation, and trash disposal. DBSCAN was tested with epsilon of 33.1, 33.2, 33.3, 33.4, 33.5 and MinPts of 2, 3, 4, while HDBSCAN was tested with MinPts of 2, 3, 4. The results of this study indicate that DBSCAN with epsilon of 33.3 and MinPts of 2 produced 3 clusters and 12 noise points, achieving a superior DBCV value of 0.276. Meanwhile, HDBSCAN with MinPts set to 2 produced 15 clusters and 10 noise points, achieving a DBCV of 0.261. Thus, DBSCAN is the best algorithm for clustering flood-prone areas on the island of Kalimantan. The results of this research demonstrate the effectiveness of DBSCAN for flood-prone area delineation, informing targeted mitigation strategies across Kalimantan.
Dynamic Panel Data Modeling of Regional Economic Growth Using Generalized Method of Moments Arellano-Bond Approach Fuad Muhajirin Farid; Yeni Rahkmawati; Selvi Annisa; Muhammad Riza Hafizi
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6376

Abstract

South Kalimantan’s regional economy remains strongly dependent on the mining and quarrying sector, raising concerns about growth persistence and structural dependence. While numerous studies have examined regional economic growth, they predominantly relied on static panel models that fail to capture dynamic adjustments and potential endogeneity issues inherent in macroeconomic. The objective of this research is to analyze the dynamic relationship between exogenous variables and economic growth in South Kalimantan and to address gaps in previous research. The method employed in this study is the Arellano–Bond Generalized Method of Moments (GMM), using balanced panel data from 12 regencies/cities in South Kalimantan over the period 2017–2025. The results indicate that lagged economic growth, the mining and quarrying sector, and realized investment have a significant and positive effect on regional economic growth. The short-run elasticity further indicates that mining and quarrying generate a stronger growth response than realized investment, confirming the continued dominance of extractive activities in the regional economy. These findings imply that South Kalimantan’s growth is dynamic but remains structurally dependent on resource-based sectors. Therefore, regional governments should optimize mining contributions by strengthening environmental governance, accelerating economic diversification, improving investor-related public services, and strengthening linkages among investment, local labor absorption, and MSME development.
Comparison of COM-Poisson and Poisson–Tweedie Regression in Handling Overdispersion Khaeriah Wahyu; Aswi Aswi; Sitti Masyitah Meliyana R
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6383

Abstract

Count data are commonly modeled using Poisson regression. However, this model has limitations when the equidispersion assumption is violated, particularly under conditions of overdispersion. This study aims to compare the performance of the COM-Poisson and Poisson–Tweedie regression models for handling overdispersion and to identify factors influencing the number of measles cases among children under five in Indonesia in 2024. The method used in this research is a quantitative approach using secondary data on laboratory-confirmed measles cases among children under five across 38 provinces in Indonesia. The data were analyzed using COM-Poisson and Poisson–Tweedie regression models. The explanatory variables include measles immunization coverage, the number of people living in poverty, the percentage of vitamin A supplementation, the percentage of exclusive breastfeeding, and the percentage of undernourished children under five. The results of this research indicate that the Poisson regression model exhibits overdispersion and is therefore not suitable for the data. Both the COM-Poisson and Poisson–Tweedie regression models can accommodate overdispersion. Based on model selection criteria, namely the Akaike Information Criterion (AIC), the Poisson–Tweedie regression model demonstrates the best performance for analyzing the number of measles cases among children under five in Indonesia in 2024. Based on the selected model, measles immunization coverage, the number of people living in poverty, and the percentage of vitamin A supplementation have a statistically significant effect on the number of measles cases among children under five. In contrast, the percentage of exclusive breastfeeding and the percentage of undernourished children under five do not show a statistically significant effect.
Spatial Autoregressive Panel Model for Analyzing the Environmental Quality Index Alimatu Qurroti Ainina; Dewi Sri Susanti; Rony Riduan
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6384

Abstract

A region’s general environmental conditions are reflected in the Environmental Quality Index (EQI). In South Kalimantan Province, differences in EQI between districts and cities indicate that the contributing factors do not operate consistently, requiring an analysis that accounts for both spatial and temporal dimensions. The aim of this research is to apply a spatial panel data regression model to analyze the effects of population density, regional gross domestic product (GRDP), human development index (HDI), sanitation access, poverty rate, and economic growth on the EQI across 13 districts and cities in South Kalimantan over the period 2016–2023. The research method used in this study involves spatial regression models, namely the Spatial Autoregressive Fixed Effect (SAR-FE) and Spatial Error Model Fixed Effect (SEM-FE) approaches with a queen contiguity spatial weight matrix. The results of the study show a spatial relationship in the EQI data, with a Moran’s I of 0.2606 in 2016 and 0.1668 in 2017. This emphasizes the importance of spatial panel data modeling. With an AIC of 1322.378 and a coefficient of determination of 0.8112, SAR-FE is the best-fitting model. The modeling results indicate a significant spatial effect, whereby the EQI of a district or city is influenced by the EQI of its neighboring regions, such that changes in environmental quality in one area may affect surrounding areas. Furthermore, access to sanitation and the poverty rate do not significantly affect the EQI, whereas population density, GRDP, HDI, and economic growth are significant, indicating that environmental quality dynamics in South Kalimantan are shaped by socioeconomic factors as well as spatial interdependencies among regions. In order to improve environmental quality and minimize negative spillover effects across nearby regions, these findings emphasize the necessity of spatially integrated environmental policies that support sustainable economic growth, human development, and interregional coordination.
Application of the Stevenson-Porter Fuzzy Time Series Method in Forecasting Oil and Gas Import Values Hairatun Hisanun; Aswi Aswi; Muhammad Fahmuddin S
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6407

Abstract

The value of Indonesia’s oil and gas imports is one of the important indicators of Indonesia’s economic growth. The high value of imports over time shows that Indonesia has not been able to manage domestic energy supply properly, which can threaten national energy security. Therefore, an accurate forecasting method is needed to forecast the value of Indonesia’s oil and gas imports. The objective of this research is to forecast the value of Indonesia’s oil and gas imports for January 2025. The method used in this study is the Stevenson–Porter fuzzy time series method, using monthly data on Indonesia’s oil and gas import values from January 2010 to December 2024. The results indicate that the forecasted value of Indonesia’s oil and gas imports for January 2025 is US$ 2,553.5 million, with a Mean Absolute Percentage Error (MAPE) of 6.21%, indicating very good forecasting accuracy. The forecast result can support policymakers in improving energy import planning and strengthening Indonesia’s national energy security.
Panel Data Regression Analysis of Socio-Economic Factors on the Human Development Index in Regencies/Cities Aneska Denadah; Bernadhita Herindri Samodera Utami; Edwin Russel; Khoirin Nisa
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6427

Abstract

The Human Development Index (HDI) is an important indicator for assessing the success of human development; however, disparities in HDI persist across regencies and cities in Lampung Province. This study aims to examine the effects of Gross Regional Domestic Product (GRDP), poverty rate, and average years of schooling on HDI using panel data from 15 regencies/cities during 2019–2024. Average years of schooling is one of the constituent indicators used to calculate HDI. Therefore, its estimated effect should be interpreted as an empirical association rather than an independent causal determinant of HDI. Panel data regression was employed using the Fixed Effect Model (FEM) estimated by the Least Squares Dummy Variable (LSDV) approach. The estimation results show that a 1% increase in average years of schooling is associated with a 0.1208% increase in HDI (β = 0.1208, p − value = 0.0109). Meanwhile, GRDP (β = −0.0548, p − value = 0.2074) and the poverty rate (β = 0.0264, p − value = 0.2587) do not have statistically significant effects on HDI. These findings indicate that educational attainment plays a more important role than the other socio-economic variables considered in explaining HDI disparities across regencies and cities in Lampung Province.
A Negative Binomial Regression Analysis of Factors Affecting the Labor Force Participation Nur Aisyah; Aswi Aswi; Wahidah Sanusi; Indy Pratiwi HR
Jurnal Varian Vol. 9 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v9i2.6587

Abstract

Labor force participation is a crucial indicator of regional economic development, providing essential evidence for effective employment policies. However, empirical studies analyzing labor force determinants frequently rely on Poisson regression, which assumes equidispersion and produces inefficient estimates when socioeconomic count data exhibit overdispersion. Despite this widespread issue, the application of Negative Binomial Regression (NBR) to model labor force participation remains limited, particularly in South Sulawesi, Indonesia. Therefore, this study aims to examine the effects of Gross Regional Domestic Product (GRDP), average years of schooling, poverty rate, and the population aged 15 and older on the labor force in South Sulawesi, while identifying the most appropriate regression model for overdispersed count data. Using a Generalized Linear Model (GLM) approach, the study compares Poisson regression and NBR using 2023 secondary data from Statistics Indonesia (BPS). Model performance was evaluated through overdispersion testing, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Results demonstrate significant overdispersion in the data, rendering the Poisson model inadequate. Conversely, NBR demonstrates superior performance with lower AIC and BIC values. Furthermore, the findings reveal that average years of schooling and the population aged 15 and above have statistically significant positive effects on the labor force, whereas GRDP and the poverty rate do not. These findings imply that educational attainment and demographic structures are stronger determinants of labor force participation than macroeconomic conditions in South Sulawesi. Ultimately, NBR provides a more robust framework for modeling such data, offering reliable empirical evidence for regional workforce planning.

Page 20 of 20 | Total Record : 198

 16   17   18   19   20 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 9 No. 2 (2026) Vol. 9 No. 1 (2026) Vol. 8 No. 3 (2025) Vol. 8 No. 2 (2025) Vol. 8 No. 1 (2024) Vol 8 No 1 (2024) Vol 7 No 2 (2024) Vol. 7 No. 2 (2024) Vol 7 No 1 (2023) Vol. 7 No. 1 (2023) Vol 6 No 2 (2023) Vol 6 No 1 (2022) Vol 5 No 2 (2022) Vol 5 No 1 (2021) Vol 4 No 2 (2021) Vol 4 No 1 (2020) Vol 3 No 2 (2020) Vol 3 No 1 (2019) Vol 2 No 2 (2019) Vol 2 No 1 (2018) Vol 1 No 2 (2018) Vol 1 No 1 (2017) More Issue