p-Index From 2020 - 2025
6.566
P-Index
This Author published in this journals
All Journal FORUM STATISTIKA DAN KOMPUTASI Media Statistika Statistika JURNAL MATEMATIKA STATISTIKA DAN KOMPUTASI IPTEK The Journal for Technology and Science CAUCHY: Jurnal Matematika Murni dan Aplikasi Sosioinforma International Journal of Advances in Intelligent Informatics Scientific Journal of Informatics JOIN (Jurnal Online Informatika) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Penelitian Pertanian Tanaman Pangan BAREKENG: Jurnal Ilmu Matematika dan Terapan SINTECH (Science and Information Technology) Journal MIND (Multimedia Artificial Intelligent Networking Database) Journal Jurnal Aplikasi Statistika & Komputasi Statistik FIBONACCI: Jurnal Pendidikan Matematika dan Matematika Inferensi International Journal of Advances in Data and Information Systems InPrime: Indonesian Journal Of Pure And Applied Mathematics Majalah Ilmiah Matematika dan Statistika (MIMS) Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Enthusiastic : International Journal of Applied Statistics and Data Science Prosiding Seminar Nasional Official Statistics Jurnal Natural Eduvest - Journal of Universal Studies Xplore: Journal of Statistics PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND OFFICIAL STATISTICS Parameter: Jurnal Matematika, Statistika dan Terapannya Scientific Journal of Informatics Journal of Mathematics, Computation and Statistics (JMATHCOS) Advance Sustainable Science, Engineering and Technology (ASSET) Indonesian Journal of Statistics and Its Applications Journal on Mathematics Education
Claim Missing Document
Check
Articles

Regresi Terboboti Geografis dengan Fungsi Pembobot Kernel Gaussian pada Kekuatan Sinyal Seluler Logananta Puja Kusuma; . Indahwati; Kusman Sadik
Xplore: Journal of Statistics Vol. 8 No. 1 (2019): 30 April 2019
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/xplore.v8i1.134

Abstract

Cellular signal strength may be affected by its location, so researches concerning signal strength need information about location and analysis method that observe spatial aspect. Spatial Regression analysis evaluates location in modeling relation between explanatory variables and response variable. One of the spatial regression analyses is Geographically Weighted Regression (GWR). This method utilizes location to create weight matrix using certain weighting function. GWR analysis with Gaussian kernel weighting function creates better model than Ordinary Least Square model. The model created using GWR is local model which parameter estimation differs in each observation point. Clustering of observation point is performed to summarize the result of GWR. The number of optimum clusters in clustering based on coefficient is five clusters while the number of optimum clusters in clustering based on p value of t test is four clusters.
Identifikasi Faktor-faktor yang Memengaruhi Hasil Akreditasi SMA di Indonesia Berdasarkan Data ARKAS Muh Nur Fiqri Adham; Budi Susetyo; Kusman Sadik; Satriyo Wibowo
Xplore: Journal of Statistics Vol. 10 No. 3 (2021)
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (540.898 KB) | DOI: 10.29244/xplore.v10i3.837

Abstract

Accreditation is an indicator of the quality of education at the education unit level. One affects the quality of education units is the school budget. School budgets are prepared in order to fulfill 8 national education standards. School budget management uses School Activity Plan and Budget Application (ARKAS) developed by the Ministry of Education, Culture, Research and Technology (Kemendikbudristek). ARKAS is an information system for managing school budget and expenditure planning. The Research is identifies the factors that influence the accreditation of high school (SMA) with accreditation as a response variable and 17 explanatory variables sourced from ARKAS and Dapodik data using ordinal logistic regression analysis. The best model stage is the model formed that has the smallest AIC value and has high model accuracy in determining the best model. The best model stage is the third model stage which is composed of 7 explanatory variables that affect the high school accreditation rating with AIC value of 1886,20 and model accuracy of 65,79%. The variables that affect to results of accreditation include school status, percentage of students eligible PIP, ratio of the number of students per number of teachers, percentage of teachers certified educators, ratio of the number of students per number of study groups, ratio of the number of students per number of computers, and ratio of the number of students per number of toilets
Perbandingan ARIMA dan Artificial Neural Networks dalam Peramalan Jumlah Positif Covid-19 Di DKI Jakarta Tri Wahyuni; Indahwati Indahwati; Kusman Sadik
Xplore: Journal of Statistics Vol. 10 No. 3 (2021)
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (425.867 KB) | DOI: 10.29244/xplore.v10i3.846

Abstract

DKI Jakarta is the center of the spread of Covid-19. This is indicated by the higher cumulative number of Covid-19 positive in DKI Jakarta compared to other provinces. The high number of cases in DKI Jakarta is a concern for all groups, so it is necessary to do forecasting to predict the number of Covid-19 positive in the next period. Accurate forecasting is needed to get better results. This study compares the Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN) methods in predicting the number of Covid-19 positive in DKI Jakarta. Forecasting accuracy is calculated using the value of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and correlation. The results show that the best model for forecasting the number of Covid-19 positive in DKI Jakarta is ARIMA(0,1,1) with drift, with a MAPE value of 15.748, an RMSE of 268.808, and the correlation between the forecast value and the actual value of 0.845. Forecasting using ARIMA(0,1,1) with drift and BP(3,10,1) models produces the best forecast for the long forecasting period of the next six weeks.
Perbandingan Performa Metode Pohon Model Logistik dan Random Forest pada Pengklasifikasian Data Purnama Sari; Kusman Sadik; Mulianto Raharjo
Xplore: Journal of Statistics Vol. 12 No. 1 (2023): Vol. 12 No. 1 (2023)
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (466.078 KB) | DOI: 10.29244/xplore.v12i1.858

Abstract

Multicollinearity and missing data are two common problems in big data. Missing data could decrease the prediction accuracy. Logistic model tree (LMT) is used to handle multicollinearity because multicollinearity does not affect the decision tree. Random forest can be used to decrease variance in prediction case. This study aimed to study the comparison of two methods, LMT and random forest, in multicollinearity and missing data in various cases using simulation study and real data as dataset. Evaluation model is based on classification accuracy and AUC measurement. The result stated that random forest had better performance if the multicollinearity level is moderate. LMT with omitted missing data is proven to have better performance for big data and when a high percentage of missing data occurred, and the multicollinearity level is severe. The next step is analysed real data with different sample size. The result stated that random forest have better performance. Omitted missing data have better performance in classification “breast cancer” data which consist 0,3 % missing data.
Kajian Metode Pohon Model Logistik (Logistic Model Tree) dengan Penanganan Ketakseimbangan Data Akmala Firdausi; Aam Alamudi; Kusman Sadik
Xplore: Journal of Statistics Vol. 11 No. 2 (2022):
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (583.431 KB) | DOI: 10.29244/xplore.v11i2.922

Abstract

Logistic model tree is a nonparametric modelling method that combines decision tree with linear logistic regression. Logistic model tree handles multicollinearity well, but is not immune to problems that arise due to data imbalance. This study was carried to compare the performance of undersampling, SMOTE, and ROSE in handling imbalanced data when used in tandem with logistic model tree. The data used in the simulation was obtained by generating random numbers following the Bernoulli distribution as the response variable and the Bivariate Normal distribution as the explanatory variables, based on five different imbalance levels. Comparisons done on the AUC value showed that logistic model trees built with methods to handle imbalanced data performed better than logistic model trees built without applying any such method on every level of tested data imbalance in classifying objects. Among those, logistic model trees built with ROSE performed better than logistic model trees built with other methods. On datasets with low level of imbalance, the performance of logistic model trees built with ROSE and undersampling do not significantly differ.
Perbandingan Kinerja Regresi Conway-Maxwell-Poisson dan Poisson-Tweedie dalam Mengatasi Overdispersi Melalui Data Simulasi Ahmad Rifai Nasution; Kusman Sadik; Akbar Rizki
Xplore: Journal of Statistics Vol. 11 No. 3 (2022): Vol. 11 No. 3 (2022)
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (310.954 KB) | DOI: 10.29244/xplore.v11i3.1018

Abstract

Poisson regression is a standard method to model count data. Modeling count data frequently causes overdispersion which means that Poisson regression is less precise to model it as Poisson regression has the assumption of equidispersion. Overdispersion can be overcome by using Conway-Maxwell-Poisson (COM-Poisson) and Poisson Tweedie (Poisson-Tw) regression. The best model is determined based on the lowest value of RMSE, absolute bias, variance of parameter estimator, AIC, and BIC. This research uses simulation data. The response variable of simulation data is generated to follow Generalized Poisson distribution with combinations of and The result of simulation study shows that COM-Poisson and Compound Poisson-Tw are the alternatives to model overdispersed count data, but COM-Poisson is better to overcome overdispersion with higher dispersion parameter.
Deep Learning Approaches for Predicting Intraday Price Movements: An Evaluation of RNN Variants on High-Frequency Stock Data Mochamad Ridwan; Kusman Sadik; Farit Mochamad Afendi
Proceedings of The International Conference on Data Science and Official Statistics Vol. 2023 No. 1 (2023): Proceedings of 2023 International Conference on Data Science and Official St
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/icdsos.v2023i1.278

Abstract

This study discusses the comparison of four recurrent neural networks (RNN) models: Simple RNN, Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bidirectional RNN (BiRNN), in forecasting minute-level stock price time series data. The performance of these four models is evaluated using the Mean Absolute Percentage Error (MAPE) on a stock dataset from Bank Central Asia (BBCA.JK). The experimental results reveal that the GRU model exhibits the best performance with an average MAPE of 0.0255%, followed by the LSTM model with an average MAPE of 0.0377%. The BiRNN model also demonstrates good performance with an average MAPE of 0.0668%, while the Simple RNN has the highest average MAPE at 0.5118%. This suggests that more complex recurrent architectures like GRU and LSTM have better capabilities in capturing patterns in high-frequency time series data. This study can be expanded by exploring other models such as CNN, conducting tests on diverse datasets, and experimenting with a wider range of hyperparameter variations. Additional variables such as economic indicators, global market data, and social data can also offer a more comprehensive understanding of factors influencing stock prices.
Classification of household poverty in West Java using the generalized mixed-effects trees model FARDILLA RAHMAWATI; KHAIRIL ANWAR NOTODIPUTRO; KUSMAN SADIK
Jurnal Natural Volume 23 Number 3, October 2023
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jn.v23i3.33079

Abstract

Dealing with fixed effects and random effects can be accomplished by combining statistical modeling and machine learning techniques. This paper discusses the modeling of fixed effects and random effects using a statistical machine-learning approach. We used the generalized mixed-effects trees (GMET), a tree-based mixed-effect model for dealing with response variables that belong to the exponential family of distributions. In this study, both simulation and actual/empirical data utilized the GMET method to discover data conditions that were appropriate for employing this approach. The simulation data was generated using different response variable generations, as well as different values of the variance of random effect and fixed effect coefficients. The findings indicated that the GMET performs similarly for different response variable generation scenarios. However, it performed better when the fixed effect value and the variance of random effects were large. When applied to the empirical data, the GMET method describes fixed effects and random effects and classifies household poverty status quite well based on the area under curve (AUC) value. It has also revealed that important variables for poverty classification are the number of household members, owning land, the type of main fuel used for cooking, and the main source of water used for drinking. In order to address the socioeconomic disparity that leads to poverty, the government may become concerned about these factors. In addition to that information, the use of regional typology as a random effect in the model has also contributed to the variation of household poverty status. Based on research, the fixed effects in mixed models do not need to be linear and GMET may be employed in grouped data structures, giving the GMET technique the ability to compete with other approaches/methods.
Study on the performance of Robust LASSO in determining important variables data with outliers ROCHYATI ROCHYATI; KUSMAN SADIK; BAGUS SARTONO; EVITA PURNANINGRUM
Jurnal Natural Volume 23 Number 1, February 2023
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jn.v23i1.26279

Abstract

A variable selection method is required to deal with regression models with many variables, and LASSO has been the most widely used methodology.  However, as several authors have noted, LASSO is sensitive to outliers in the data.  For this reason, the Robust-LASSO approach was introduced by applying some weighting schemes for each sample in the data.  This research presented a comparative study of the three weighting schemes in Robust LASSO, namely Huber-LASSO, Tukey-LASSO, and Welsch-LASSO.  The study did a rich simulation containing many scenarios with various characteristics on the covariance structures of the explanatory variable, the types of outliers, the number of outliers, the location of active variables, and the number of variables.  The study then found that Tukey-LASSO outperformed Huber-LASSO and Welsch-LASSO in identifying significant variables.  The Robust LASSO performance generally decreased as the covariances among explanatory variables increased and the data dimension increased.  Exploration of sembung leaf extract data shows that the data is high dimensional data which contains outliers of about 14,28% on the response variable and about 25,71% on the explanatory variables.  Based on the research, the number of variables selected using the Tukey-LASSO method was nine compounds, Huber-LASSO and Welsch-LASSO were eight compounds, and LASSO 13 compounds.  The Tukey-LASSO prediction accuracy is superior to the other three methods.
Pengaruh Penggunaan Random Undersampling, Oversampling, dan SMOTE terhadap Kinerja Model Prediksi Penyakit Cardiovascular (CVD) Uswatun Hasanah; Agus Mohamad Soleh; Kusman Sadik
Jurnal Matematika, Statistika dan Komputasi Vol. 21 No. 1 (2024): SEPTEMBER 2024
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v21i1.35552

Abstract

Cardiovascular Disease (CVD) or commonly known as Heart Disease is a leading cause of mortality globally, prompting extensive research into predictive models to assess individual risk and plan preventive measures. Machine learning approaches such as Random Forest, Support Vector Machine (SVM), and LASSO Logistic Regression have showed promise. Recent studies have indicated that traditional resampling methods like Random Oversampling, Random Undersampling, and SMOTE may not significantly improve model discrimination. This study aims to evaluate the impact of these techniques on the performance of Cardiovascular Disease (CVD) prediction models, utilizing data from the UCI Machine Learning Heart Disease database. By employing LASSO Logistic Regression, Random Forest, and Support Vector Machine (SVM) with resampling techniques, including Random Oversampling, Random Undersampling, and SMOTE. This research seeks to enhance understanding of model performance in addressing class imbalances within the dataset and contribute to refining cardiovascular disease (CVD) prediction strategies. This study demonstrates that the use of the SMOTE technique significantly enhances the performance of cardiovascular disease (CVD) prediction models. Specifically, when combined with the Random Forest algorithm, SMOTE achieves the best performance in terms of accuracy, sensitivity, and specificity. This highlights the importance of selecting appropriate resampling techniques to handle class imbalance in datasets. Consequently, this research contributes to refining CVD prediction strategies and provides new insights into improving prediction accuracy in imbalanced medical data.
Co-Authors . Erfiani . Indahwati A.Tuti Rumiati Aam Alamudi Abdullah, Adib Roisilmi Achmad Fauzan Agus Mohamad Soleh Ahmad Rifai Nasution Aji Hamim Wigena Akbar Rizki Akbar Rizki Akbar Rizki Akmala Firdausi Amalia, Rahmatin Nur Anadra, Rahmi Ananda Shafira Anang Kurnia Andespa, Reyuli Andi Okta Fengki ASEP SAEFUDDIN Astari, Reka Agustia Astari, Reka Agustia Aulya Permatasari Azka Ubaidillah Bagus Sartono Budi Susetyo Budi Susetyo Cici Suhaeni Cici Suhaeni Dito, Gerry Alfa Dwi Agustin Nuriani Sirodj Efriwati Efriwati Embay Rohaeti Eminita, Viarti EVITA PURNANINGRUM FARDILLA RAHMAWATI Farit Mochamad Afendi Fitrianto, Anwar Haikal, Husnul Aris Hari Wijayanto Hasnataeni, Yunia Hazan Azhari Zainuddin Hermawati, Neni I Gusti Ngurah, Sentana Putra I Made Sumertajaya I Wayan Mangku Indahwati Indahwati Indahwati Intan Arassah, Fradha Iqbal, Teuku Achmad Isnanda, Eriski Khairi A N Khairil Anwar Notodiputro Khikmah, Khusnia Nurul Khusnul Khotimah Kusni Rohani Rumahorbo Latifah, Leli Lili Puspita Rahayu Logananta Puja Kusuma M Soleh, Agus Mochamad Ridwan Mochamad Ridwan, Mochamad Mohammad Masjkur Muh Nur Fiqri Adham Muhammad Yusran Mulianto Raharjo Naima Rakhsyanda Nisrina Az-Zahra, Putri Nur Khamidah NURADILLA, SITI Nusar Hajarisman Pangestika, Dhita Elsha Parwati Sofan, Parwati Purnama Sari Rifqi Aulya Rahman Rizki, Akbar Rizqi, Tasya Anisah ROCHYATI ROCHYATI Sahamony, Nur Fitriyani Saleh, Agus Muhammad Satriyo Wibowo Siregar, Jodi jhouranda Siti Raudlah Sitti Nurhaliza Soleh, Agus M Suhaeni, Cici Supriatin, Febriyani Eka Tendi Ferdian Diputra Titin Suhartini Titin Suhartini, Titin Tri Wahyuni Uswatun Hasanah Utami Dyah Syafitri Viarti Eminita Widhiyanti Nugraheni Yenni Angraini Yenni Kurniawati Yuli Eka Putri