cover
Contact Name
Etis Sunandi
Contact Email
esunandi@unib.ac.id
Phone
6281295949261
Journal Mail Official
jsds_statistika@unib.ac.id
Editorial Address
Jl. WR. Supratman Kelurahan Kandang Limun Kota Bengkulu
Location
Kota bengkulu,
Bengkulu
INDONESIA
Journal of Statistics and Data Science
Published by Universitas Bengkulu
ISSN : -     EISSN : 28289986     DOI : https://doi.org/10.33369/jsds
Established in 2022, Journal of Statistics and Data Science (JSDS) publishes scientific papers in the fields of statistics, data science, and its applications. Published papers should be research-based papers on the following topics: experimental design and analysis, survey methods and analysis, operations research, data mining, machine learning, statistical modeling, computational statistics, time series, econometrics, statistical education, and other related topics. All papers are reviewed by peer reviewers consisting of experts and academics across universities and agencies. This journal publishes twice a year, which are March and October.
Articles 36 Documents
Forecasting A Weekly Red Chilli Price in Bengkulu City Using Autoregressive Integrated Moving Average (ARIMA) and Singular Spectrum Analysis (SSA) Methods Putriasari, Novi; Nugroho, Sigit; Rachmawati, Ramya; Agwil, Winalia; Sitohang, Yosep O
Journal of Statistics and Data Science Vol. 1 No. 1 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i1.21007

Abstract

Red chili occupies a strategic position in the Indonesian economic structure because its use applies to almost all Indonesian dishes. Therefore, controlling the price of red chili is anecessity to maintain national economic stability. The purpose of this research is to forecast a red chili weekly price using ARIMA and SSA based on the weekly data of chili prices from January 2016 - December 2019 sourced from Statistics Indonseia (BPS) Branch Office of Bengkulu Province. The data have been analyzed using software R. Based on MAPE, ARIMA (2,1,2) provides the best forecasting with value 0.49% while SSA 10.64%.
Agglomerative Nesting (AGNES) Method and Divisive Analysis (DIANA) Method For Hierarchical Clustering On Some Distance Measurement Concepts Wijuniamurti, Susi; Nugroho, Sigit; Rachmawati, Ramya
Journal of Statistics and Data Science Vol. 1 No. 1 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i1.21009

Abstract

Clustering data through hierarchical approach could be performed by Agglomerative Nesting (AGNES) Method and Divisive Analysis (DIANA) Method. The objective of this research is to compare both the methods based on Euclid and Manhattan distance measurements. Of this research the clustering procedures of agglomerative method are conducted by exploring all techniques including single linkage, complete linkage, average linkage, and Ward. The data used are the National Socio-Economic Survey (SUSENAS) data which are selected specifically for the percentage of over 5 year old residents in each province, for both living in urban or rural, who access the internet in the last 3 months in 2017 but classified according purpose of accessing. By applying Mean Square Error (MSE) for 2 and 3 clusters, it can be concluded that the single linkage technique is the best performance of clustering procedure for both Euclidean and Manhattan distances.
Partitioned Design Matrix Method for Two Factors Multivariate Design Alvionita, Renny; Nugroho, Sigit; Chozin, Mohammad
Journal of Statistics and Data Science Vol. 1 No. 1 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i1.21010

Abstract

Factorial experiment often involves large data sets and the use of generalized inverse for the data analysis. It becomes less manageable as the data increased. The objective of this study is to evaluate the accuracy of partitioned design matrix method for two factors multivariate design. The design matrix is partitioned into several sub-matrices based on their source of variation. The partitioned design matrix method in two factors multivariate is much simpler than usual sigma summation method in calculating the sum of product matrix and the degrees of freedom. This method could also be used in explaining the derivation of the statistics for testing the hypothesis of the equality of the means which corresponds to the source of variation.
A Comparison of Weighted Least Square and Quantile Regression for Solving Heteroscedasticity in Simple Linear Regression Fransiska, Welly; Nugroho, Sigit; Rachmawati, Ramya
Journal of Statistics and Data Science Vol. 1 No. 1 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i1.21011

Abstract

Regression analysis is the study of the relationship between dependent variable and one or more independent variables. One of the important assumption that must be fulfilled to get the regression coefficient estimator Best Linear Unbiased Estimator (BLUE) is homoscedasticity. If the homoscedasticity assumption is violated then it is called heteroscedasticity. The consequences of heteroscedasticity are the estimator remain linear and unbiased, but it can cause estimator haven‘t a minimum variance so the estimator is no longer BLUE. The purpose of this study is to analyze and resolve the violation of heteroscedasticity assumption with Weighted Least Square(WLS) and Quantile Regression. Based on the results of the comparison between WLS and Quantile Regression obtained the most precise method used to overcome heteroscedasticity in this research is the WLS method because it produces that is greater (98%).
Simulation of Sample Determination Quick Count Legislative Elections In Bengkulu City Gumilar, Andri Tresna; Nugroho, Sigit; Keraman, Buyung
Journal of Statistics and Data Science Vol. 1 No. 1 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i1.21012

Abstract

In this research illustrates the simulation of quick count of sampling for the year 2014 Legislative Election in Bengkulu City, which has a data acquisition result for 589 TPS. The problem in this research is how to know the sample size and the right sampling method for Legislative Election in Bengkulu City on Year 2014. The purpose of this research is to know the sample size and the quick count calculation sampling method that can predict the actual vote result for Legislative Election. The method used in the calculation of fast calculation consists of three methods, simple random sampling, cluster random sampling and multistage random sampling. From the population data of 589 polling stations (TPS) into the population, the sample size was taken as much as 120 TPS or about 20% of the population, based on the results of calculations for sample sizes in a limited population. After the sample was selected, a sample simulation of 100 times for each method and simulation results was tested for compatibility with the chi-squared test. Based on the test results, it can be concluded that for sample size 120 TPS taken by simple random sampling method, cluster random sampling or multistage random sampling can predict the actual vote result in Legislative Election Year 2014 in Bengkulu with margin of error 5%. For efficiency consideration simple random sampling method can be selected.
Price Prediction Using ARIMA Model of Monthly Closing Price of Bitcoin Pratama, Apriliyanus Rakhmadi
Journal of Statistics and Data Science Vol. 1 No. 2 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i2.22689

Abstract

The rising of bitcoin’s user as a digital currency and investments causing an instability and an uncertainty in price movement and increasing the risk of trading, therefore in this study we try to forecast the future value of bitcoin price using ARIMA Models. 2 candidate models are selected by the lowest value of AIC and using the performance indicators ME, RSME, MAE, MPE, and MAPE conclude ARIMA (1,1,0) are the best ARIMA model, then the next 5 months future price forecasted using the best model. While ARIMA (1,1,0) is the best model, the model failed to follow price movement as shown in the forecasted price.
Integration Cluster and Path Analysis Based on Science Data in Revealing Stunting Incidents Marchamah, Mamlu’atul; Fernandes, Adji Achmad Rinaldo; Solimun; Wardhani, Ni Wayan Surya; Putri, Henida Ratna Ayu
Journal of Statistics and Data Science Vol. 1 No. 2 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i2.23570

Abstract

The purpose of this research is to utilize big data to explore the factors that influence the prevalence of stunting in Wajak Regency, model these factors using integrated cluster analysis and` path analysis model, and develop an information system for stunting incidence modeling. This study uses a descriptive and explanative approach, namely using Discourse Network Analysis, cluster analysis, path analysis, and integration of cluster and path analysis. The sample of this research is children under five in Wajak District who were selected using stratified random sampling. The distance measure that has the highest model goodness value in modeling using the integration of cluster analysis with path analysis is the Mahalanobis distance measure. The cluster analysis with Mahalanobis distance produces 3 clusters where cluster one is a toddler who has a low stunting category, cluster two is a group of toddlers who has a moderate stunting category, and cluster three is a group of toddlers who has a high stunting category. The originality of this study is the application of Discourse Network Analysis analysis to obtain new variables followed by a comparison of three distances namely euclidean, manhattan, and mahalanobis in modeling using cluster integration and parametric paths.
Measles Disease Analysis in Bengkulu Province Using Zero Inflated Poisson Regression and Zero Inflated Negative Binomial Regression Azagi, Ilham
Journal of Statistics and Data Science Vol. 1 No. 2 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i2.24028

Abstract

Zero Inflated Poisson regression (ZIP) and Zero Inflated Negative Binomial (ZINB) regression were used if there was overdispersion and no multicollinearity in the data. This study aims to analyze measles in Bengkulu Province using the ZIP and ZINB regression models. Among them are selecting the best model, seeing the influential variables from the best model, and predicting the results of the best model. The data used is one dependent variable, namely the number of measles cases (Y) in each puskesmas and six independent variables (X) namely the percentage of measles immunization, the amount of malnutrition, the percentage of exclusive breastfeeding, the percentage of vitamin A, the percentage of proper sanitation, and the percentage of healthy house. The results of this study, the ZIP regression model formed is a discrete model for , namely ln()=-5.042-0.007X1-0.014X3+0.094X4 and a zero inflation model for , namely logit()= -3.656+0.101X4-0.054X6, while the ZINB regression model formed is a discrete model for , namely ln()=-9,289+0.120X4 and a zero inflation model for , namely logit()=- 17.841+0.205X4. The AIC value of the ZINB regression model is 255.249, which is smaller than the AIC value of the ZIP regression model of 331.467, so the ZINB regression model is better to use. The influential variable in this study is the percentage of vitamin A administered. There is not much difference between predicted results and the actual data.
Achievement Cluster of Covid-19 Vaccination at the South Bengkulu Health Center Using Agglomerative Hierarchical Clustering Sari, Devni Prima; Sumita, Nurmaya
Journal of Statistics and Data Science Vol. 1 No. 2 (2022)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v1i2.24082

Abstract

The concerns of many people and the lack of vaccine information are significant obstacles to achieving the Covid-19 vaccination target. The government and health groups must be ready to provide correct vaccine information to reduce public doubts. To evaluate the vaccine implementation, this is necessary to cluster the area regarding the achievement of the vaccination target. Clustering this area can be done using the Agglomerative Hierarchical Clustering method. In this study, clustering was carried out using Covid-19 vaccination data at the South Bengkulu Health Center involving six variables. Three clusters were formed for the clustering process: the first dose of Covid-19 vaccination, the second dose of Covid-19 vaccination, and the first Booster vaccination. Each cluster is represented by low, medium, and high clusters
Survival Analysis of Students Not Graduated on Time Using Cox Proportional Hazard Regression Method and Random Survival Forest Method Arib, Muhammad Arib Alwansyah
Journal of Statistics and Data Science Vol. 2 No. 1 (2023)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v2i1.24312

Abstract

Higher education is a place to educate the next generation of the nation in terms of academic and non-academic. Basically every college tries to maximize the graduation of its students, both in quantity and quality. The undergraduate education program is targeted to complete 8 semesters of study or can also be taken in less than 8 semesters and a maximum of 14 semesters. Many factors are thought to affect the length of student study, both internal and external factors. Based on the factors that are thought to affect the length of study of the student, it is necessary to conduct research to determine what factors have a significant effect on the length of study of the student. The method that can be used to determine these factors is survival analysis using cox proportional hazard regression and random survival forest. Factors that affect the length of study using cox proportional hazard regression is GPA, while by using the random survival forest method, the factors that influence the length of study of students are GPA, gender, and part time. Based on the comparison using the C-Index method, random survival forest is a suitable method to use in the data because the C-Index error value is 26.9% which is smaller than the cox proportional hazard which is 27.8%.

Page 1 of 4 | Total Record : 36