Jurnal Statistika dan Matematika (Statmat)
P-ISSN : 2655-3724 E-ISSN : 2720-9881 Jurnal Statmat UNPAM: Jurnal Statistika dan Matematika Universitas Pamulang is a means of publication of scientific articles and research with concentrations of Statistics, Pure Mathematics, Applied Mathematics, Computational Mathematics, Educational Mathematics, and other research articles related to Statistics and Mathematics. Mathematics Department, Faculty of Mathematics and Natural Sciences, University of Pamulang publishes this journal, since 2019, which scheduled periodically every six months (twice a year).
Articles
18 Documents
Search results for
, issue
"Vol 8 No 1 (2026)"
:
18 Documents
clear
<![CDATA[Pengelompokan Kecamatan di Kabupaten Banyumas Berdasarkan Produktivitas Hasil Tanaman Pangan Menggunakan Metode K-Means Clustering ]]>
<![CDATA[Retno Dwi Astuti]]>;
<![CDATA[Puspita, Dian]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.51667
<![CDATA[Significant differences in food crop productivity in each sub-district in Banyumas are a major concern that needs to be addressed. This handling is specifically given to sub-districts with low productivity categories. However, the sub-district groups according to their categories are not yet known. Therefore, this study aims to group sub-districts in Banyumas Regency based on food crop productivity. Grouping is done using the K-Means Clustering method. The data used are data on the harvest productivity of five food crop commodities according to sub-districts in Banyumas Regency in 2023. The results obtained that there are five clusters with three clusters having at least one type of food crop that is less productive and two clusters which all types of food crops are productive.]]>
<![CDATA[Penerapan Generalized Additive Model Spline Dalam Analisis Dinamika Tingkat Pengangguran Terbuka di Provinsi Sulawesi Selatan ]]>
<![CDATA[Zalzabila, Jelita]]>;
<![CDATA[Anna Islamiyati]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.52430
<![CDATA[Analisis regresi adalah metode yang sangat penting dalam memodelkan hubungan antara variabel, di mana variabel prediktor berpengaruh terhadap variabel respon. Namun, regresi linear konvensional memiliki beberapa keterbatasan, terutama ketika asumsi linearitas dan normalitas tidak terpenuhi. Dalam konteks ini, Generalized Additive Model (GAM) muncul sebagai alternatif yang lebih fleksibel. GAM mampu menangani hubungan non-linear antara variabel prediktor dan respon, serta tidak mengharuskan variabel respon untuk berdistribusi normal. GAM menggunakan pendekatan regresi nonparametrik, seperti penalized spline, untuk mengestimasi fungsi smoothing yang dapat menyesuaikan pola data secara otomatis. Pendekatan ini juga membantu mencegah overfitting, yang sering menjadi masalah dalam pemodelan data yang kompleks. Penelitian ini bertujuan untuk menerapkan GAM spline dalam memodelkan faktor-faktor yang memengaruhi Tingkat Pengangguran Terbuka (TPT) di Provinsi Sulawesi Selatan. Tahapan penelitian mencakup pengujian linearitas, penentuan titik knot, dan parameter penghalus optimal. Selanjutnya, pemodelan GAM dilakukan dengan menggunakan penalized spline pada variabel non-linear. Hasil pemodelan menunjukkan bahwa variabel Rata-Rata Lama Sekolah (RLS) dan Produk Domestik Regional Bruto (PDRB) memiliki pengaruh signifikan terhadap TPT, sementara variabel lainnya tidak menunjukkan signifikansi. Dengan demikian, model GAM penalized spline berhasil memodelkan hubungan antara faktor-faktor yang memengaruhi TPT secara efektif. Penelitian ini memberikan pemahaman yang lebih dalam bahwa peningkatan RLS dan PDRB dapat berkontribusi dalam menurunkan TPT di Sulawesi Selatan, yang merupakan informasi penting bagi pengambil kebijakan dalam merumuskan strategi pengurangan pengangguran.]]>
<![CDATA[Comparison of Moving Average and Double Exponential Smoothing Methods in Rice Production Forecasting Based on NTB Satu Data ]]>
<![CDATA[Arbyati, Asri Mustika]]>;
<![CDATA[Maharani, Andika Ellena Saufika Hakim]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.52806
<![CDATA[The rapid development of technology in the industry 4.0 era has led to the emergence of the data literacy era, where data is no longer merely supporting information but has become a strategic asset in decision-making. Recognizing the importance of data utilization, the West Nusa Tenggara/Nusa Tenggara Barat (NTB) Provincial Government launched the NTB Satu Data program through Governor Regulation No. 45 of 2021. This program provides an open, standardized, and integrated sectoral data platform managed by the NTB Communication, Information, and Statistics Agency. Through this platform, data is collected, validated, analyzed, and visualized so that it can be utilized for evidence-based policy planning. This study utilizes annual rice production data from 2001 to 2024 from the NTB Satu Data portal to forecast rice production in 2025. Two commonly used time series forecasting methods, Moving Average (MA) and Double Exponential Smoothing (DES), are applied and compared in terms of accuracy. Evaluation was conducted using the Mean Absolute Percentage Error (MAPE) and Mean Absolute Deviation (MAD) metrics. The analysis results show that the DES (Holt) method produced a MAPE of 9.455% and a MAD of 158.533, outperforming the MA order 2 method with a MAPE of 9.746% and a MAD of 161.700. These findings indicate that DES is more adaptive in capturing historical trend patterns and more effective in modeling production changes over time. The results of this study are expected to provide input for local governments in designing food security policies that are responsive to production dynamics. Utilizing these forecasts will enable more appropriate allocation of resources, increased preparedness for potential food supply disruptions, and strengthening of sustainable food security in NTB Province.]]>
<![CDATA[Pemodelan Tren Pencarian Google Penyakit Penyebab Kematian Tertinggi di Indonesia Dengan Metode Loop Prophet ]]>
<![CDATA[Qurani, Anggun]]>;
<![CDATA[Chandra Sari Widyaningrum]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.52858
<![CDATA[The Loop Prophet method is a time series forecasting approach that utilizes the Facebook Prophet model iteratively (looping) to automatically process multiple variables or keywords. This study aims to predict the weekly search trend on Google for the leading causes of death in Indonesia, taking into account trend, yearly seasonality, and weekly seasonality components, as well as to evaluate model performance using error metrics such as NMAE, NRMSE, and MAPE. The dataset consists of weekly Google Trends search data for selected diseases during the period from September 2020 to July 2025. The results indicate that the Loop Prophet model successfully captures both trend and seasonal patterns. Based on the evaluation criteria, models categorized as “very good” were obtained for the keywords “Stroke”, “Diabetes”, and “Diare”. The “good” category was obtained for “Serangan Jantung”, “Sirosis Hati”, “Penyakit Paru”, “COPD”, dan “Neonatal”. The keyword of “Tuberkulosis” was categorized as “good enough”. Meanwhile, the “poor” category was found for “Kanker Paru-Paru” dan “Pneumonia”, which tend to have fluctuating patterns influenced by incidental events. These findings demonstrate that the Loop Prophet method is effective for time series analysis with complex seasonal patterns, although its performance decreases for diseases with highly irregular search trends.]]>
<![CDATA[Generalized LASSO Regression Menggunakan K-Nearest Neighbors Pada Data Persentase Penduduk Miskin Indonesia ]]>
<![CDATA[Sulistyo, Sheilla Amanda]]>;
<![CDATA[Anna Islamiyati]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.53420
<![CDATA[Generalized LASSO Regression merupakan pengembangan dari metode LASSO dengan memberikan penalti tidak hanya pada setiap parameter secara terpisah, tetapi juga pada kelompok parameter yang saling terkait. Pendekatan K-Nearest Neighbors (KNN) menentukan besaran penalti berdasarkan kedekatan data dalam ruang fitur sehingga model dapat memilih variabel yang berelasi secara lokal, meningkatkan kemampuan mengenali pola berurutan atau kelompok pada data berdimensi tinggi tanpa mengurangi kemudahan interpretasi. Penelitian ini bertujuan untuk memperoleh parameter tuning optimal pada model Generalized LASSO Regression dengan KNN dan mendapatkan variabel yang berpengaruh terhadap persentase penduduk miskin. Metode penelitian ini terdiri dari dua tahap umum, yakni penentuan tetangga menggunakan KNN dan pemodelan Generalized LASSO Regression dengan pendekatan KNN untuk pendugaan persentase penduduk miskin. Hasil analisis menunjukkan bawa model terbaik diperoleh pada KNN K=3dengan nilai parameter tuning sebesar 0,028 menghasilkan koefisien determinasi 91,5% dan RMSE sebesar 0,130. Model Generalized LASSO Regression dengan pendekatan KNN terbukti dapat menangani masalah multikolinearitas dan efek wilayah untuk mengetahui variabel yang berpengaruh terhadap persentase penduduk miskin. Model ini dapat menjadi alat bantu dalam perencanaan kebijakan di Indonesia dengan fokus wilayah.]]>
<![CDATA[Model Struktural Faktor Sosio-Ekonomi Yang Memengaruhi Tingkat Kesehatan di Indonesia: Pendekatan Partial Least Squares ]]>
<![CDATA[Priscillia Maharani, Cinta]]>;
<![CDATA[Gunawan, Risky]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.53694
<![CDATA[Pembangunan manusia merupakan tolok ukur fundamental dalam menilai keberhasilan pembangunan suatu wilayah, dengan kesehatan sebagai variabel hasil yang krusial. Penelitian ini bertujuan untuk menganalisis model struktural pengaruh variabel laten Pendidikan dan Ekonomi terhadap Kesehatan, dengan Kemiskinan sebagai variabel mediasi. Penelitian ini menggunakan pendekatan kuantitatif dengan metode Partial Least Squares Structural Equation Modeling (PLS-SEM). Data yang digunakan merupakan data sekunder dari Badan Pusat Statistik untuk 38 provinsi di Indonesia pada tahun 2024. Evaluasi model awal menunjukkan perlunya revisi akibat adanya masalah multikolinearitas, loading factor yang rendah, dan jalur yang tidak signifikan. Model akhir yang direvisi menunjukkan tingkat kecocokan yang baik dengan nilai SRMR sebesar 0,041. Hasil penelitian menunjukkan bahwa variabel laten Ekonomi berpengaruh negatif signifikan terhadap Kemiskinan (koefisien jalur = -0,851) dan berpengaruh positif signifikan terhadap Kesehatan (koefisien jalur = 0,765). Variabel Ekonomi mampu menjelaskan 71,7% varians Kemiskinan dan 57,4% varians Kesehatan. Dalam model akhir, variabel Pendidikan serta peran mediasi Kemiskinan tidak terbukti signifikan. Studi ini menyimpulkan bahwa faktor ekonomi merupakan pendorong utama yang secara langsung memengaruhi penurunan angka kemiskinan dan peningkatan status kesehatan di Indonesia.]]>
<![CDATA[Spatial Modeling in Public Health: A Review of Geographically Weighted Poisson Regression (GWPR) Applications ]]>
<![CDATA[Raihannabil, Syfriza Davies]]>;
<![CDATA[Halma, Karini]]>;
<![CDATA[Hutagalung, Reghita Maria]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.54205
<![CDATA[Geographically Weighted Poisson Regression (GWPR) is an important approach in analyzing spatial count data, especially in the field of public health. However, its application in Indonesia still has various methodological weaknesses. This study aims to critically review the suitability and application of the GWPR model, as well as analyze aspects of statistical assumptions, weighting function selection, model evaluation, and methodological innovation. This study uses an article review approach of 10 research articles that apply GWPR in public health. The review results show that most studies have not explicitly articulated research gaps and novelty, and have ignored crucial offset variables in count data. Spatial heterogeneity testing is often performed incorrectly using the BP test instead of visual exploration through thematic maps. The selection of weighting functions and bandwidths is often not based on objective evaluation. Additionally, many studies have not conducted multicollinearity checks and tests of the assumption of equidispersion, which directly impact model validity. Descriptive analysis and visualization of local parameters through maps remain limited, hindering contextual interpretation. Finally, some studies fail to include model goodness-of-fit evaluations such as AIC or pseudo-R², making it impossible to demonstrate the superiority of GWPR over global models objectively. These findings underscore the importance of upholding statistical validation principles and methodological transparency in GWPR modeling to produce accurate and relevant spatial analyses for regional policy-making.]]>
<![CDATA[Analysis of Factors Influencing Poverty in South Sumatra Using the Poisson Regression Model ]]>
<![CDATA[Manik, Jolius Saut Mangaraja]]>;
<![CDATA[Fitri Maya Puspita]]>;
<![CDATA[Sisca Octarina]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.54763
<![CDATA[Poverty remains a key development issue for the government, including in South Sumatra Province. This study aims to analyze the factors influencing poverty levels at the district/city level using a Poisson regression model. The independent variables used include the open unemployment rate, education level, Gross Regional Domestic Product (GRDP) per capita, and the percentage of the population working in the informal sector. The data used are secondary data obtained from the Central Statistics Agency (BPS) for the most recent available year. The analysis shows that several variables significantly influence the number of poor people in South Sumatra, where increasing open unemployment and a high proportion of informal workers tend to increase the number of poor people. Conversely, increasing education and GRDP per capita contribute to reducing poverty levels. The Poisson regression model proved appropriate for modeling the number of incidents (count) data in this study. These findings are expected to provide input for local governments in formulating more targeted poverty alleviation policies.]]>
<![CDATA[Classification of Pension Benefit Adequacy for Civil Servants in Pontianak City Using the C4.5 Algorithm ]]>
<![CDATA[Indah Maharani, Dwi]]>;
<![CDATA[Tamtama, Ray]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.54960
<![CDATA[The development of information technology has encouraged the use of data-driven analysis to support decision-making in the governmental sector, including within the civil service pension system. This study aims to classify the adequacy of pension benefits received by retired Civil Servants in Pontianak City using the C4.5 algorithm. Pension benefit adequacy is determined by comparing the amount of basic pension received with household expenditures, which are calculated using the average monthly per capita expenditure in Pontianak City. The dataset consists of 322 retirees with variables including retirement age, years of service, last education, rank, and number of dependents. The model was developed using several training–testing data proportions, namely 70:30, 75:25, and 80:20. Model evaluation was conducted using accuracy, sensitivity, and specificity based on the confusion matrix. The results show that the 80:20 proportion produces the best model, achieving 100% accuracy, 100% sensitivity, and 100% specificity. The generated decision tree indicates that the most influential variable is the number of dependents, followed by rank and years of service. These findings suggest that household expenditure burdens and employment characteristics play a crucial role in determining pension adequacy. The resulting model is expected to assist pension management institutions in formulating data-driven policies to improve the welfare of retirees.]]>
<![CDATA[Clinic of Mathematics with the PPLAM Approach: Efforts to Improve Students’ Mathematics Learning in Manokwari ]]>
<![CDATA[Lubis, Loria Amisah]]>;
<![CDATA[Trigarcia Maleachi Randa]]>;
<![CDATA[Esther Ria Matulessy]]>;
<![CDATA[Chrisaria Palungan]]>;
<![CDATA[Dahlia Gladiola Rurina Menufandu]]>
<![CDATA[ STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 8 No 1 (2026) ]]>
Publisher : <![CDATA[Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Pamulang, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32493/sm.v8i1.54979
<![CDATA[This study aims to analyze the effectiveness of the Mathematics Clinic in overcoming the difficulties of seventh-grade junior high school students in integer operations. The research focused on improving students’ learning outcomes through a short learning intervention consisting of a pretest, structured practice, and a posttest conducted within a single day. The method employed was a quasi-experimental design with a one-group pretest–posttest dengan Embedded Learning Analytics (PPLAM). The subjects were 25 seventh-grade students purposively selected based on their identified difficulties in learning mathematics. Data were collected through achievement tests (pretest and posttest) and students’ practice records. The data analysis included a paired t-test to measure the difference between pretest and posttest scores, the calculation of Normalized Gain (N-Gain) to assess the effectiveness of improvement, and effect size to determine the magnitude of the intervention’s impact. In addition, a simple learning analytics approach was applied to examine the relationship between practice quality and posttest results. The findings revealed a significant improvement in students’ learning outcomes with . The mean N-Gain score of 0.578 indicated a medium level of improvement, while the effect size (Cohen’s d = 2.164) was categorized as very large. Furthermore, learning analytics analysis showed an R2 = 0,70 suggesting that practice quality positively contributed to students’ posttest performance. It can be concluded that the Mathematics Clinic is effective as an alternative learning strategy to address difficulties in integer operations, even when implemented within a short time frame.]]>
