cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Norisca Lewaherilla
Contact Email
lewaherillanorisca@gmail.com
Phone
+6285243401733
Journal Mail Official
jurnalvariance@gmail.com
Editorial Address
Jl. Ir. M. Putuhena, Poka-Ambon, 97233, Maluku, Indonesia
Location
Kota ambon,
Maluku
INDONESIA
Variance : Journal of Statistics and Its Applications
Published by Universitas Pattimura
ISSN : 26858738     EISSN : 2685872X     DOI : -
Core Subject : Education,
Mathematics
Jurnal ini diterbitkan oleh Program Studi Statistik Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Pattimura, Ambon. Jurnal ini diterbitkan 2 kali pada bulan Juni dan Desember.
Arjuna Subject : -
Articles 106 Documents
 7   8   9   10   11 
STRUCTURAL EQUATION MODELING-GENERALIZED STRUCTURED COMPONENT ANALYSIS TO ANALIZING STRUCTURE OF POVERTY IN INDONESIA IN 2022 Marukai, Nur Amalia; Wungguli, Djihad; Nashar, La Ode; Nasib, Salmun K.; Asriadi, Asriadi; Abdussamad, Siti Nurmardia
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page167-174

Abstract

Structural Equation Modeling - Generalized Structured Component Analysis (SEM-GSCA) is a component-based method suitable for limited sample sizes. GSCA is appropriate for structural models that include variables with reflective and formative indicators. This study utilizes the Alternating Least Square (ALS) parameter estimation. Iterations in ALS are used to achieve minimal residuals. Additionally, this study employs jackknife resampling to obtain standard error estimates. This study aims to identify the poverty model structure in Indonesia and examine the relationships among poverty, human resources, economic, and health variables. The results of the structural model of poverty in Indonesia are explained as follows: the influence of human resources and economic variables on poverty is insignificant, while the health variable significantly negatively influences poverty. Furthermore, the health variable significantly influences human resources, and both human resources and health significantly influence the economy.
MARKOV CHAIN ANALYSIS FOR PREDICTION OF MONTHLY AVERAGE TEMPERATURE PATTERNS AT PATTIMURA METEOROLOGICAL STATION AMBON 2015 - 2024 Selangur, Djudid Sintje; Lestaluhu, Musfa Rizaldi; Qadry, Alwatia Al; Huwae, Angel Gressovin; Toumahuw, Imanuella; Lewen, Dorothy H.; Seknun, Fitri R.; Namkatu, Jalianti; Yudistira, Yudistira
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page199-208

Abstract

Weather has a significant impact on human activities, making accurate weather forecasting an important necessity. This study aims to analyze the patterns of climate element changes at the Pattimura Ambon Meteorological Station using the Markov Chain approach to identify climate transition patterns, estimate steady-state time, and predict the climate in 2025. Monthly secondary climate element data for the period 2015-2024 were obtained from the Maluku Province BPS, categorized into three conditions: cold (<25°C), normal (25°C-26.5°C), and hot (>26.5°C). The data were analyzed using the Markov Chain method with calculations of the transition probability matrix, matrix convergence, and steady-state distribution. The research results indicate that the system reaches equilibrium after 47 periods with a long-term distribution: cold condition 2.85%, normal 35.66%, and hot 61.76%. The hot condition has the highest stability with a probability of remaining in the same state at 91.8%. The 2025 prediction indicates that monthly temperature probabilities gradually move toward the steady-state distribution, illustrating the dominance and persistence of hot conditions in the long term. The analysis results provide important implications for agricultural planning, tourism, infrastructure, and disaster mitigation in the city of Ambon in the face of climate change.
ANALYSIS OF THE EFFECTIVENESS OF INFRASTRUCTURE DEVELOPMENT ON POVERTY LEVELS IN TANGERANG REGENCY IN 2024 Fitriawati, Andi; Virhafiyanti, Yunita; Madonna, Nora
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page175-186

Abstract

Poverty is defined as a condition in which a portion of the population lives with a monthly per capita expenditure below the poverty line. Addressing poverty remains a major challenge for sustainable development, and one strategic approach is infrastructure development. This study analyzes the effectiveness of education, health, and transportation infrastructure, as independent variables, in reducing poverty, as a dependent variable, in Tangerang Regency in 2024. The study employs multiple linear regression because it allows the simultaneous examination of the relationship between a single dependent variable and multiple independent variables. The results indicate that the three infrastructure variables simultaneously significantly affect poverty levels, as shown by an F-statistic of 3.572 and a p-value of 0.02813 at the 5% significance level. The coefficient of determination (R²) of 0.3001 suggests that infrastructure development explains 30.01% of poverty reduction, while other factors influence the remaining 69.99%. However, the partial test results show that none of the infrastructure variables individually has a significant effect on poverty. These findings suggest that infrastructure development contributes to poverty alleviation, though its sectoral impact remains limited. Enhancing equity and improving quality across infrastructure sectors are therefore essential to maximize and broaden its benefits.
ANALYSIS OF INVESTMENT RISK IN MALUKU PROVINCE USING MEAN-VARIANCE APPROACH ON LOCAL OWN-SOURCE REVENUE (PAD) Bakarbessy, Lusye; Talakua, Mozard Winston; Ilwaru, Venn Yan Ishak
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page187-198

Abstract

This study aims to analyze investment risks in Maluku Province using the Mean-Variance approach on the Local Own-Source Revenue (PAD) data. The method used in this study is a quantitative analysis of time-series data on PAD from 2015 to 2022. The mean-variance model is used to calculate the rate of return and risk of each PAD component and to construct an efficient frontier as a basis for optimal decision-making. The results show that the regional tax PAD component offers a high rate of return with relatively low risk, potentially making it a stable source of revenue for local governments. These findings provide a basis for optimizing PAD allocation to improve fiscal stability and the sustainability of regional development.
ECONOMIC PROJECTION OF BALIKPAPAN AS A BUFFERING CITY FOR INDONESIA’S NEW CAPITAL Silfiani, Mega; Fitriani, Yustina
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page209-218

Abstract

As part of Indonesia’s capital relocation plan to East Kalimantan, Balikpapan plays a critical role as a supporting city, facing opportunities and challenges in infrastructure, economic stability, and public services. This study forecasts two key economic indicators: monthly inflation and annual Gross Regional Domestic Product (GRDP), using Error, Trend, Seasonal (ETS) and Autoregressive Integrated Moving Average (ARIMA) methods. For monthly inflation, the SARIMA(0,1,1)(1,0,0)12 model outperforms ETS(A,N,N) with a lower RMSE, providing higher accuracy in capturing inflation dynamics. For annual GRDP, both ETS(A,N,N) and ARIMA(0,0,0) yield similar accuracy, with ARIMA slightly better. These findings support data-driven planning to maintain price stability and foster economic growth. Accurate projections ensure Balikpapan’s readiness as a sustainable, resilient city, aligning with SDG 8 (Economic Growth) and SDG 11 (Sustainable Cities and Communities).
EVALUATING NEARMISS AND SMOTE FOR VEHICLE INSURANCE FRAUD CLAIM CLASSIFICATION WITH A RANDOM FOREST CLASSIFIER Yusuf, Feby Indriana; Handamari, Endang Wahyu
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss2page219-230

Abstract

This study evaluates the detection of fraudulent car insurance claims in unbalanced data by comparing two resampling techniques, namely NearMiss (undersampling) and SMOTE (oversampling), combined with Random Forest. The public dataset, consisting of 1,000 observations and 40 features, was preprocessed for missing value handling, label encoding, and min–max normalization, and split into 70% training data and 30% test data. Three scenarios were evaluated: original data (unbalanced), NearMiss, and SMOTE, using accuracy, precision, sensitivity (recall), specificity, and F1-score evaluations. The analysis results show that NearMiss provides the most balanced performance for antifraud purposes, with a sensitivity of 0.865, an F1-score of 0.667, and an accuracy of 0.787. For the original unbalanced data, the model achieved a sensitivity of 0.297 and an accuracy of 0.767. SMOTE achieved the highest precision (0.567) and accuracy (0.783), but its sensitivity was lower than that of NearMiss. These findings confirm that the selection of resampling techniques must be aligned with operational objectives: NearMiss is more appropriate when the priority is to capture as many fraud cases as possible, while SMOTE is more suitable when false positive control is prioritized.

Page 11 of 11 | Total Record : 106

 7   8   9   10   11 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 2 (2025): VARIANCE: Journal of Statistics and Its Applications Vol 7 No 1 (2025): VARIANCE: Journal of Statistics and Its Applications Vol 6 No 2 (2024): VARIANCE: Journal of Statistics and Its Applications Vol 6 No 1 (2024): VARIANCE: Journal of Statistics and Its Applications Vol 5 No 2 (2023): VARIANCE: Journal of Statistics and Its Applications Vol 5 No 1 (2023): VARIANCE: Journal of Statistics and Its Applications Vol 4 No 2 (2022): VARIANCE: Journal of Statistics and Its Applications Vol 4 No 1 (2022): VARIANCE: Journal of Statistics and Its Applications Vol 3 No 2 (2021): VARIANCE: Journal of Statistics and Its Applications Vol 3 No 1 (2021): VARIANCE: Journal of Statistics and Its Applications Vol 2 No 2 (2020): VARIANCE: Journal of Statistics and Its Applications Vol 2 No 1 (2020): VARIANCE: Journal of Statistics and Its Applications Vol 1 No 2 (2019): VARIANCE: Journal of Statistics and Its Applications Vol 1 No 1 (2019): VARIANCE: Journal of Statistics and Its Applications More Issue