cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hasih Pratiwi
Contact Email
hpratiwi@mipa.uns.ac.id
Phone
+6282134673512
Journal Mail Official
ijas@mipa.uns.ac.id
Editorial Address
Study Program of Statistics, Universitas Sebelas Maret, Surakarta 57126, Indonesia
Location
Kota surakarta,
Jawa tengah
INDONESIA
Indonesian Journal of Applied Statistics
Published by Universitas Sebelas Maret
ISSN : -     EISSN : 2621086X     DOI : https://doi.org/10.13057/ijas
Core Subject : Economy, Science, Agriculture, Social,
Agriculture, Biological Sciences & Forestry Computer Science & IT Earth & Planetary Sciences Economics, Econometrics & Finance Environmental Science
Indonesian Journal of Applied Statistics (IJAS) is a journal published by Study Program of Statistics, Universitas Sebelas Maret, Surakarta, Indonesia. This journal is published twice every year, in May and November. The editors receive scientific papers on the results of research, scientific studies, and problem solving research using statistical method. Received papers will be reviewed to assess the substance of the material feasibility and technical writing.
Arjuna Subject : Matematika - Statistik dan Probabilitas
Articles 8 Documents
 1 
Search results for , issue "vol 8, no 2 (2025)" : 8 Documents clear
Pemetaan Daerah Rawan Bencana di Pulau Sulawesi menggunakan Metode Density-Based Spatial Clustering of Applications with Noise (DBSCAN) Havinka Angel Salsabilla; Nandini Lova Diani; Abimanyu Arya Ramadhan; M. Al Haris
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.106040

Abstract

Indonesia terletak pada pertemuan tiga lempeng tektonik aktif sehingga memiliki tingkat kerawanan yang tinggi terhadap bencana alam seperti gempa bumi, banjir, letusan gunung api, dan tanah longsor. Pulau Sulawesi merupakan salah satu wilayah dengan aktivitas seismik dan hidrometeorologi yang tinggi, sehingga identifikasi daerah rawan bencana menjadi penting dalam upaya pengurangan risiko dan perencanaan mitigasi yang efektif. Penelitian ini bertujuan untuk memetakan daerah rawan bencana di Pulau Sulawesi menggunakan algoritma Density-Based Spatial Clustering of Applications with Noise (DBSCAN). DBSCAN merupakan metode klasterisasi berbasis kepadatan yang mampu mengidentifikasi pola spasial tanpa harus menentukan jumlah klaster di awal serta dapat mendeteksi data pencilan (outlier). Data yang digunakan adalah data sekunder dari Badan Nasional Penanggulangan Bencana (BNPB) tahun 2020–2024 yang mencakup kejadian bencana di seluruh kabupaten/kota di Pulau Sulawesi. Variabel yang dianalisis meliputi frekuensi kejadian banjir, tanah longsor, cuaca ekstrem, kekeringan, gempa bumi, letusan gunung api, dan gelombang pasang. Sebelum proses klasterisasi, data dinormalisasi menggunakan metode Min–Max. Hasil terbaik diperoleh pada parameter ε = 0,28 dan MinPts = 5, yang menghasilkan dua klaster utama dan satu kelompok noise. Klaster 1 menunjukkan wilayah dengan tingkat kejadian bencana tertinggi, terutama banjir, tanah longsor, dan cuaca ekstrem. Klaster 0 mencakup wilayah dengan intensitas bencana sedang, sedangkan kelompok noise terdiri atas wilayah dengan tingkat kejadian bencana yang rendah atau pola bencana yang tidak jelas. Penerapan algoritma DBSCAN terbukti efektif dalam pemetaan kerawanan bencana karena mampu menangani distribusi spasial yang tidak merata serta mengungkap pola tersembunyi. Hasil penelitian ini diharapkan dapat menjadi dasar dalam pengembangan strategi mitigasi bencana yang lebih terarah. Penelitian selanjutnya disarankan untuk menambahkan indikator kerentanan sosial-ekonomi serta memperluas cakupan data.Kata kunci: DBSCAN; Sulawesi; Klasterisasi Spasial; Pemetaan Bencana; Mitigasi RisikoIndonesia is located at the confluence of three active tectonic plates, making it highly vulnerable to natural disasters such as earthquakes, floods, volcanic eruptions, and landslides. Sulawesi Island is one of the regions with the highest seismic and hydro-meteorological activity in Indonesia, so identifying its disaster-prone areas is crucial for effective risk reduction and mitigation planning. This study aims to map disaster-prone areas in Sulawesi Island using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. DBSCAN is a density-based clustering method that is able to identify spatial patterns without determining the number of clusters from the start, as well as detect outlier data. The data used is secondary data from National Disaster Management Authority (BNPB) for 2020–2024 covering disaster events in all districts/cities in Sulawesi. The variables analyzed include the frequency of floods, landslides, extreme weather, droughts, earthquakes, volcanic eruptions, and tidal waves. The data was normalized using the Min-Max method before the clustering process. The best results were obtained at parameters ε = 0.28 and MinPts = 5, resulting in two main clusters and one noise group. Cluster 1 shows areas with the highest disaster occurrences, especially floods, landslides, and extreme weather. Cluster 0 includes areas with moderate disaster intensity, while the noise group consists of areas with low or unclear disaster patterns. The application of DBSCAN has proven effective for disaster vulnerability because it is able to handle uneven spatial distribution and reveal hidden patterns. These results are expected to be the basis for developing more targeted disaster mitigation strategies. Further research is recommended to add socio-economic vulnerability indicators and expand data coverage.Keywords: DBSCAN; Sulawesi; Spatial Clustering; Disaster Mapping; Risk Mitigation 
Penerapan GWR dan MGWR dengan Pembobot Kernel Adaptive Tricube pada Pemodelan Prevalensi Stunting di Provinsi Jawa Tengah Imas Fitri Ningrum; Sri Sulistijowati Handajani; Respatiwulan Respatiwulan
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.94657

Abstract

Jawa Tengah merupakan salah satu provinsi dengan prevalensi stunting yang tinggi di Indonesia pada tahun 2022 sebesar 20,8% dan hampir mendekati prevalensi stunting di Indonesia sebesar 21,6%. Wilayah di Jawa Tengah beragam dalam hal geografi, ekonomi, sosial budaya, kualitas sumber daya manusia, dan ketersediaan sumber daya alam. Regresi spasial digunakan untuk memodelkan faktor-faktor yang mempengaruhi prevalensi stunting di Jawa Tengah dengan mempertimbangkan pengaruh lokasi. Perbedaan karakteristik antar lokasi menyebabkan heterogenitas spasial, sehingga masalah tersebut diatasi dengan pemodelan menggunakan geographically weighted regression (GWR). Pemodelan dengan GWR memberikan hasil bahwa tidak ada heteroskedastisitas pada salah satu variabel, sehingga pemodelan juga dilakukan menggunakan mixed geographically weighted regression (MGWR) dengan kernel tricube tertimbang adaptif. Namun, dari analisis, model GWR memberikan hasil yang lebih baik daripada model MGWR. Unit sampel dalam penelitian ini adalah 35 kabupaten/kota di Provinsi Jawa Tengah. Model GWR untuk memodelkan prevalensi stunting di Jawa Tengah menghasilkan model yang lebih baik dengan nilai AIC yang lebih kecil dibandingkan dengan model MGWR. Hasil penelitian menunjukkan bahwa balita yang kekurangan gizi memiliki pengaruh positif terhadap stunting, sedangkan bayi baru lahir yang menerima IMD, balita yang menerima vitamin A, dan pengeluaran riil per kapita memiliki pengaruh negatif terhadap stunting.kata kunci: tricube adaptif; GWR; MGWR; stuntingCentral Java is one of the provinces with a high prevalence of stunting in Indonesia in 2022 at 20.8% and is almost close to the prevalence of stunting in Indonesia at 21.6%. The regions in Central Java are diverse in terms of geography, economy, socio-culture, quality of human resources, and availability of natural resources. Spatial regression was used to model the factors that influence the prevalence of stunting in Central Java by considering the influence of location. The characteristics between locations cause heterogeneity, so the modeling used is Geographically Weighted Regression (GWR). Because one variable is not locally significant, modeling is also carried out using Mixed Geographically Weighted Regression (MGWR) with adaptive tricube kernel weighted. However, from the analysis, the GWR model gave better results than the MGWR model. The GWR model for modeling stunting prevalence in Central Java produces a better model with an AIC value of 148.883 and R^2 of 88.01% compared to the MGWR model, which only provides an AIC value of 190.371 and R^2 value of 47.66%. Based on the analysis results with the GWR model using adaptive tricube weighted, the factors influencing the prevalence of stunting in Central Java Province are newborns getting early breastfeeding initiation (IMD), toddlers with malnutrition, toddlers getting vitamin A, and real expenditure per capita.Keywords: adaptive tricube; GWR; MGWR; stunting
Exploring Statistical Power and Mediation Analysis: Understanding the Impact of Antecedent-Mediator-Outcome Relationships Szilárd Nemes
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.93376

Abstract

This paper explores the phenomenon of statistical power stagnation and decline in mediation analysis, specifically focusing on the interplay between the antecedent variable, mediator, and outcome. Mediation analysis is a critical statistical tool used to understand the causal pathways between variables. However, statistical power may not always increase with stronger relationships between the antecedent and mediator, often stagnating or even declining due to variance inflation caused by multicollinearity. We provide a in detail examination of this issue, including key theoretical concepts, the mathematical foundations of variance inflation, and the impact of mediator-antecedent correlations on power. A simulation study further illustrates how varying these correlations affects statistical power, variance estimates, and possible bias in mediation effects. Our findings indicate that while increasing the strength of the relationship between the antecedent and mediator improves mediation detection initially, beyond a certain threshold, it results in inflated variance estimates, leading to decreased precision and power. Variance inflation of the mediated effect is more accentuated than variance inflation of regression coefficients.Keywords: mediation; variance inflation; Sobel test
Comparative Analysis of Fuzzy Mamdani Method and Fuzzy Sugeno Method in Predicting Household Electricity Consumption Costs Luthfia Zahra; Mashuri Mashuri
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.103436

Abstract

Electricity has become an essential part of our daily lives. As technology has rapidly developed, many modern activities and devices have become highly dependent on electricity. The more electricity that is used, the higher the monthly cost. This cost is influenced by usage patterns and various uncertain factors. Fuzzy logic is one approach that can be used in decision support systems in the face of uncertainty like this. This study aims to apply the Mamdani and Sugeno fuzzy methods based on house building area, number of electronic devices, number of family members, and income to determine which method more accurately predicts household electricity consumption costs based on the mean absolute percentage error (MAPE) value. Data for this study were obtained through questionnaires and interviews with residents of Margorejo Village. Data processing yielded a MAPE value of 12.3% for the Mamdani method and a MAPE value of 9.9% for the Sugeno method. Based on these results, the MAPE value for the Sugeno method is smaller than that for the Mamdani method. Therefore, it can be concluded that the Sugeno method is more accurate for predicting household electricity consumption costs in Margorejo Village.Keywords: Mamdani Method, Sugeno Method, MAPE.
Deteksi Polycystic Ovary Syndrome (PCOS) Berbasis Machine Learning: Kombinasi SMOTE, Random Forest, Gradient Boosting, dan Bayesian Optimization Naufalia Alfiryal; Kusman Sadik; Cici Suhaeni; Agus Mohamad Soleh
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.109931

Abstract

Polycystic ovary syndrome (PCOS) merupakan gangguan endokrin yang umum terjadi pada wanita usia reproduktif. Kondisi ini dapat menyebabkan gangguan ovulasi, ketidakseimbangan hormon, resistensi insulin, serta meningkatkan risiko penyakit kardiovaskular, obesitas, dan gangguan psikologis. Meskipun prevalensinya cukup tinggi, sekitar 75% kasus PCOS masih belum terdiagnosis dalam praktik klinis akibat kompleksitas gejala dan keterbatasan metode diagnosis yang digunakan saat ini. Untuk mengatasi permasalahan tersebut, penelitian ini mengusulkan pendekatan berbasis machine learning guna meningkatkan akurasi dan efisiensi deteksi PCOS. Penelitian ini membandingkan performa dua algoritma pembelajaran terawasi, yaitu random forest dan gradient boosting, dalam melakukan prediksi PCOS. Dataset yang digunakan diperoleh dari repositori publik dan memuat berbagai fitur klinis yang berkaitan dengan PCOS. Untuk menangani permasalahan ketidakseimbangan kelas, metode synthetic minority over-sampling technique (SMOTE) diterapkan pada data pelatihan. Selain itu, bayesian optimization digunakan untuk melakukan penyetelan hiperparameter pada masing-masing model agar diperoleh performa yang optimal. Evaluasi performa model dilakukan menggunakan beberapa metrik, dengan area under the curve–receiver operating characteristic (AUC-ROC) sebagai metrik utama. Hasil penelitian menunjukkan bahwa model Gradient Boosting memberikan performa terbaik dengan nilai AUC sebesar 0,8983 dan nilai recall sebesar 0,95, yang mengindikasikan sensitivitas tinggi dalam mengidentifikasi kasus PCOS. Temuan ini menunjukkan bahwa kombinasi SMOTE dan bayesian optimization efektif dalam meningkatkan akurasi prediksi, khususnya pada dataset medis yang tidak seimbang. Pendekatan yang diusulkan memiliki potensi untuk diintegrasikan ke dalam sistem pendukung keputusan klinis guna mendukung proses skrining PCOS yang lebih dini dan andal.Polycystic ovary syndrome (PCOS) is a common endocrine disorder among reproductive-aged women. This condition can lead to ovulatory dysfunction, hormonal imbalance, insulin resistance, and an increased risk of cardiovascular disease, obesity, and psychological disorders. Despite its high prevalence, approximately 75% of PCOS cases remain undiagnosed in clinical settings due to the complexity of symptoms and limitations of current diagnostic methods. To address this issue, a machine learning-based approach is proposed to improve the accuracy and efficiency of PCOS detection. This study compares the performance of two supervised learning algorithms random forest and gradient boosting for PCOS prediction. The dataset used was obtained from a public repository and contains various clinical features associated with PCOS. To address the class imbalance problem, the synthetic minority over-sampling technique (SMOTE) was applied to the training data. Additionally, bayesian optimization was employed to fine-tune the hyperparameters of each model for optimal performance. Model performance was evaluated using several metrics, with the area under the curve–receiver operating characteristic (AUC-ROC) as the primary measure. The Gradient Boosting model achieved the best results, with an AUC of 0.8983 and a recall of 0.95, indicating high sensitivity in identifying positive PCOS cases. These findings demonstrate that the combination of SMOTE and Bayesian Optimization is effective in enhancing predictive accuracy, especially in imbalanced medical datasets. The proposed approach shows promise for integration into clinical decision-support systems to facilitate earlier and more reliable PCOS screening.Kata Kunci: Bayesian optimization; gradient boosting; PCOS; random forest; SMOTE.Keywords : Bayesian optimization; gradient boosting; PCOS; random forest; SMOTE.
Analisis Ketahanan Remaja Perempuan di Perdesaan terhadap Pernikahan Dini di Indonesia dengan Log-logistic Gamma Shared Frailty Survival Model Werri Yulianto; Hardius Usman
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.87185

Abstract

Pada tahun 2022, Badan Pusat Statistik (BPS) mencatat bahwa angka pernikahan dini di wilayah perdesaan dua kali lebih tinggi dibandingkan perkotaan. Praktik ini masih didukung sebagai bagian dari tradisi, meskipun merupakan bentuk pelanggaran terhadap hak anak dan kekerasan terhadap perempuan. Penelitian ini menggunakan analisis survival dengan model shared frailty log-logistic gamma berdasarkan data Susenas 2022 untuk mengkaji faktor-faktor yang memengaruhi ketahanan remaja perempuan perdesaan usia 15–24 tahun terhadap pernikahan dini. Hasil penelitian menunjukkan bahwa tingkat pendidikan perempuan, tingkat kesejahteraan, dan jumlah anggota rumah tangga menjadi faktor pengaruh yang paling besar terhadap ketahanan remaja perempuan di perdesaan dari pernikahan dini. Selain itu, terdapat pengaruh faktor tak terobservasi (shared frailty) pada setiap kabupaten/kota yang menunjukkan variasi karakteristik antar wilayah dari ketahanan remaja perempuan di perdesaan terhadap pernikahan dini. Pencegahan pernikahan dini memerlukan pendekatan komprehensif melalui peningkatan akses pendidikan, pemberdayaan ekonomi perempuan, serta penguatan sosialisasi dan pendidikan kesehatan reproduksi.In 2022, BPS recorded that the number of early marriage in rural areas was twice than urban areas. Rural communities still support early marriage as a form of local tradition and culture, even though early marriage is a form of violence against women that violates children's rights. This study uses survival analysis with a shared frailty log-logistic gamma model to analyze the variables that influence the resilience of rural Indonesian girls aged 15-24 against early marriage based on data from the National Socioeconomic Survey (Susenas 2022). The results show that the level of education, welfare level, and number of household members have the greatest influence on the resilience of rural adolescent girls to early marriage. In addition, there is an influence of unobserved factors (shared frailty) in each district/city, which shows variations in characteristics between regions in terms of the resilience of rural adolescent girls to early marriage in Indonesia. Preventing early marriage requires a holistic approach through the empowerment of women, especially in rural areas, by increasing access to education, economic independence, and support for entrepreneurship programs. In addition, raising public awareness through social outreach, institutional cooperation, and strengthening sex education and reproductive health are important steps to reduce early marriage.Kata kunci: Pernikahan dini, analisis survival, shared frailty.Keywords: Early marriage, survival analysis, shared frailty.
Pemodelan Spatial Autoregressive Confused pada Prevalensi Ketidakcukupan Konsumsi Pangan di Nusa Tenggara Tahun 2023 Baharuddin Baharuddin; Agusrawati Agusrawati; Irma Yahya
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.103618

Abstract

Analisis regresi terhadap prevalensi ketidakcukupan konsumsi pangan (prevalence of undernourishment, PoU) di Provinsi Nusa Tenggara Barat dan Provinsi Nusa Tenggara Timur menunjukkan adanya otokorelasi spasial, baik pada peubah respon maupun pada komponen galat. Kondisi tersebut menyebabkan pelanggaran terhadap asumsi regresi linier. Penelitian ini bertujuan untuk menangani kedua bentuk otokorelasi spasial tersebut melalui pemodelan spatial autoregressive confused (SAC). Data PoU menurut kabupaten/kota bersumber dari Badan Pangan Nasional, sementara peubah bebas berasal dari publikasi Badan Pusat Statistik. Hasil penelitian ini menunjukkan bahwa model SAC memberikan dugaan parameter yang lebih akurat dibandingkan dengan model regresi linier. Faktor-faktor yang berpengaruh signifikan terhadap PoU di suatu kabupaten/kota meliputi produksi beras per kapita, realisasi bantuan sosial pangan per kapita, PoU di daerah tetangga, dan suku-suku galat di daerah tetangga.A regression analysis of the prevalence of undernourishment (PoU) in the provinces of Nusa Tenggara Barat and Nusa Tenggara Timur indicates the presence of spatial autocorrelation, both in the response variable and the error component. This condition violates the assumptions of linear regression. This study aims to address both forms of spatial autocorrelation by employing the spatial autoregressive confused (SAC) model. The 2023 PoU data by regency/city in Nusa Tenggara were sourced from the National Food Agency, while the explanatory variables were obtained from BPS-Statistics publications. The results of this study show that the SAC model provides more accurate parameter estimates compared to the linear regression model. The factors that significantly influence the PoU in a given regency/city include per capita rice production, per capita realization of food social assistance, the PoU levels in neighboring regions, and error terms in surrounding areas.Kata kunci: pembobot spasial berbasis jarak; prevalensi ketidakcukupan konsumsi pangan; regresi spasialKeywords: Distance-based weight; prevalence of undernourishment; spatial regression
Gold Price Forecasting with Long Short Term Memory (LSTM) and ARIMAX Method Raisa Naura Adila; Abdurakhman Abdurakhman
Indonesian Journal of Applied Statistics Vol 8, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v8i2.97739

Abstract

Gold is very popular investment instrument due to its annual prices increases. In the long term, gold prices follow a nonlinear pattern, but in the short term, there are fluctuations influenced by various factors, including global market dynamics, monetary policy, and overall economic conditions. Therefore, predicting gold prices is an important step in minimizing risk and maximizing profits for investors. In this study, we analyze the performance of two methods for forecasting global gold prices, namely long short term memory (LSTM) and autoregressive integrated moving average with exogenous variables (ARIMAX). Data used is weekly global gold price data from August 1, 2000, to June 1, 2024. The variables used are Close as the dependent variable and Open as the exogenous variable. The data used is stationary data through the differencing process and algorithmic transformation to overcome non-stationarity issues. The best LSTM model uses the Tanh activation function with 30 LSTM units, 10 timesteps, and a dropout of 0.01, resulting in a MAPE value of 5.323%. The best ARIMAX model obtained was the ARIMAX (0,1,1) model, with a MAPE value of 0.55% for the test data and 0.61% for the training data. The research results, indicate that the higher accuracy of ARIMAX reflects its suitability for linear data such as gold prices, but the accuracy of LSTM which is below 10% still performs well for more complex data patterns.Keywords: gold price; forecasting; LSTM; arimax.

Page 1 of 1 | Total Record : 8

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 9, No 1 (2026) Vol 8, No 2 (2025) Vol 8, No 1 (2025) Vol 7, No 2 (2024) Vol 7, No 1 (2024) Vol 6, No 2 (2023) Vol 6, No 1 (2023) Vol 5, No 2 (2022)