Jurnal Statistika dan Aplikasinya

Front Matter JSA Volume 7 Issue 2, December 2023

2024-01-09T17:20:40+07:00

Back Matter JSA Volume 7 Issue 2, December 2023

2024-01-09T03:42:45+07:00

Regresi Logistik Ordinal untuk Memodelkan Predikat Lulusan Perguruan Tingggi

2024-01-11T10:04:30+07:00

Logistic regression is an alternative model that can model the relationship between a categorical response variable and one or more categorical, continuous predictor variables, or a combination of categorical and continuous predictor variables. Based on the number of categories in the response variable, the logistic regression model consists of a dichotomous logistic regression model and a polychotomous regression model. The dichotomous logistic regression model is a logistic regression model that has two categories in the response variable and has a Bernoulli distribution. In comparison, the polychotomous logistic regression model is a logistic regression model that has three or more categories and a multinomial distribution. The polychotomous logistic regression model is divided into two models, namely the multinomial logistic regression model and ordinal logistic regression. This research aims to examine ordinal logistic regression modeling and its application to the predicate of graduates of the undergraduate program at the Faculty of Mathematics and Natural Sciences, Mulawarman University (FMIPA UNMUL) for the 2020 graduation period. The results of the research show that the factors that have a significant influence on the predicate of graduates of the FMIPA UNMUL undergraduate program are gender and admission route. Female graduates of the FMIPA UNMUL undergraduate program have a greater chance of achieving satisfactory and very satisfactory predicates compared to achieving a cum laude predicate. Graduates of the FMIPA UNMUL undergraduate program who are accepted through the SMMPTN admission route have a lower chance of achieving satisfactory and very satisfactory predicates compared to achieving a cum laude predicate.

Ambang Batas Reasuransi Non-Proporsional Menggunakan Tail Value-At-Risk (TVaR) dari Distribusi Peluang Campuran

2024-01-11T10:05:30+07:00

One of the tasks of banking institutions is to channel funds to the public through loan products. Banking institutions transfer the risk of non-performing loans to insurance companies and then partially reinsured to reinsurers. The purpose of this study is to determine the non-proportional reinsurance threshold based on the risk of loss of the 20% largest loan principal, using the Tail Value-at-Risk (TVaR) method. The threshold value will be estimated using a sample of 5,000 loans principal. The loan characteristics can be described by a Mixture Gamma Distribution consisting of components with different weights and parameters. The weights and parameters are 19% from the Gamma distribution with parameters α = 2.45 and β = 0.04, 34.5% from Gamma with parameters α = 8.29 and β = 0.07, and 46.5% from Gamma with parameters α = 30 and β = 0.13. Analysis using TVaR produces a threshold value of 274.9 million rupiah. In real cases, if the claim value exceeds 274.9 million rupiah. The insurance company will bear a value of 274.9 million rupiah and the reinsurer will bear the difference in the size of the claim against the threshold limit.

Pemodelan Besar Klaim menggunakan Distribusi Berekor dan Tail-Value-at-Risk (TVaR) pada Data Sampel Badan Penyelenggara Jaminan Sosial (BPJS) Kesehatan

2024-01-11T10:06:55+07:00

Information about amount of insurance claims is needed by insurer to set premium or other decisions in the future. Amount of claims modeling is a way to determine the characteristics of a distribution of claims data and can be used to predict the amount of claims that may occur. A commonly used model for amount of insurance claims data is the distribution model for heavy tails. The discussion in this article focuses on modeling amount of insurance claims using Lognormal, Pareto and Weibull distributions, and also using Gamma distribution for comparison. The data used is sample data from Badan Penyelenggara Jaminan Sosial (BPJS) Kesehatan in 2015-2016. The data contains membership data and details of the amount of each participant's claim. The analysis is carried out to find out the best candidate model that matches the amount of insurance claims data for both inpatient and outpatient categories. In addition, the Tail-Value-at-Risk (TVaR) of the model will be calculated to determine the amount of capital that will be required with a 75% confidence level. Based on the results of the study, the best model for large data samples of claims for outpatient and inpatient categories is the Lognormal model. TVaR for the outpatient category is Rp492,596 and for the inpatient category is Rp7,672,726.

Evaluasi Perbandingan Kinerja Algoritma Cheng and Church Biclustering Terhadap Algoritma Clustering Klasik K-Means untuk Mengidentifikasi Pola Distribusi Barang Ekspor Indonesia

2024-01-11T10:08:08+07:00

Clustering is a process of grouping data into several groups (clusters) so that data in one cluster has a homogeneous level of similarity and data between clusters has heterogeneous similarity. A common example of a clustering algorithm is K-Means Clustering. Compared with classical clustering algorithms, the biclustering algorithm is a two-dimensional data grouping process. The biclustering algorithm functions to find data submatrices, namely row subgroups and column subgroups that have high correlation. One example of a biclustering algorithm is Cheng and Church Biclustering (CC Biclustering). The aim of this research is to evaluate the performance of the biclustering algorithm against classical clustering algorithms. Analysis applied to CC Biclustering and K-Means Clustering to identify distribution patterns of Indonesian export goods in the period 2013 to 2022. Based on research results, the optimal scenario for the K-Means algorithm is scenario 2, that is the application of the 7 cluster K-Means algorithm with pre- processing data scaling. Meanwhile, the optimal scenario for the CC Biclustering algorithm is scenario 1, that is the application of the CC Biclustering algorithm with a tolerance value of 0.10 with data scaling pre-processing. However, from these two scenarios, based on the MSR/Volume value, it was concluded that the best scenario is scenario 1 in the application of the CC Biclustering algorithm which has an MSR/Volume value of 0.077.

Determinan Kejahatan Siber (Cybercrime) di ASEAN Tahun 2015-2020: Pendekatan Panel Data Regression with Random Effect

2024-01-11T10:08:52+07:00

The use of information and communication technology in ASEAN is massive and growing. This development not only has a positive impact, but also a negative one. In addition to advancements in various fields, criminality is also increasing. ASEAN is the fastest growing digital market in the world. As digital technology becomes more integrated into our lives, cybercrime will increase exponentially. This study aims to determine the overview and variables that affect cybercrime in ASEAN in 2015-2020. This research uses secondary data from ITU, World Bank, UNDP, and Transparency International the Global Coalition Against Corruption. Through descriptive analysis, it is found that the value of the Global Cybersecurity Index (GCI) in ASEAN has increased, but there is still a cybersecurity gap between countries in ASEAN. Through the panel data regression equation formed, it is found that economic growth, mobile broadband users, and average years of schooling significantly affect the GCI in ASEAN in 2015-2020. Meanwhile, the variables of mobile cellular users, technology exports, and corruption perception index do not have a significant effect. Therefore, governments in ASEAN countries are also expected to continue to increase economic growth and allocate budgets for technical implementation of cybersecurity. In addition, the government should maintain the stability of the number of mobile broadband users, and increase the average number of mobile broadband users.

Klasterisasi Desa di Provinsi Jawa Barat Berdasarkan Indeks Pembangunan Desa (IPD) Tahun 2021 Menggunakan Algoritma K-Prototypes

2024-01-11T10:09:26+07:00

Cluster analysis is a method used to group data with similar characteristics. There are various clustering methods adapted to different types of data. K-Prototypes is a clustering method that can be applied to mixed numerical and categorical data. The data used in this study are mixed numerical and categorical data derived from the Village Potential data in 2021. The aim of this research is to group villages in West Java based on variables from the Indeks Pembangunan Desa (IPD). Clustering using three clusters adapted to village status according to IPD resulted in 931 villages in cluster-1, 1880 villages in cluster-2, and 2104 villages in cluster-3. The characteristics of cluster-1 villages are villages that have adequate health and education facilities and good infrastructure conditions. Cluster-2 has an average numeric variable lower than cluster-1 but higher than cluster-3.

Analisis Faktor-Faktor yang Menjelaskan Tingkat Kematian Akibat Bunuh Diri pada Negara-Negara di Benua Asia dan Eropa

2024-01-11T10:09:58+07:00

Many Indonesians still view mental health as a taboo subject and people with mental disorders are treated like a disgrace. As a result, they have difficulty getting the help they need and can end in suicide. The objects of research are countries in Asia and Europe. The purposes of this research are to analyze factors explaining death rate due to suicide and to work out the grouping results of Asian and European countries. The methods used are multiple linear regression, Ward’s method clustering, and Biplot mapping. Based on the analysis result, it is obtained that factors of having no religion, alcohol consumption, and psychiatrists’ availability have significant positive relationships with suicide rate. Factors of income and unemployment have significant negative relationships with suicide rate. Factor of education level has no significant effect with suicide rate. Two groups of countries are formed, namely group 1 consisting of 46 countries and group 2 consisting of 44 countries. Result of mapping based on the groups using the Biplot method is able explain 63,7% of data diversity. Group 1 is a group of countries that have a high unemployment rate and low values in: suicide rate, proportion of irreligious people, Gross Domestic Product (GDP) per capita, number of psychiatrists, and education level. Group 2 is a group of countries that have high values in: suicide rate, proportion of irreligious people, GDP per capita, number of psychiatrists, and education level while the unemployment rate is low.

Perbandingan Metode K-Means Clustering dengan Self-Organizing Maps (SOM) untuk Pengelompokan Provinsi di Indonesia Berdasarkan Data Potensi Desa

2024-01-11T10:10:22+07:00

K-Means is a method of grouping data into several different groups so that data that has similar characteristics is made into one group while data that has different characteristics is made into a different group, where this method works by minimizing the distance between the data and the cluster center. In addition to K-Means clustering, there is also the Self Organizing Maps (SOM) method which is an undirected method, meaning that layers consisting of neurons are arranged into groups based on input values, where each data grouping process is based on the characteristics or features of the data. Clustering is carried out in Provinces in Indonesia based on village potential data in 2021 with the aim of knowing the performance comparison of K-Means clustering and Self Organizing Maps (SOM). Determination of the optimal number of clusters is carried out using the Elbow method, the results in the study obtained 3 clusters for both K-Means clustering and Self Organizing Maps (SOM). The clustering results are evaluated using the Davies Bouldin Index (DBI) value and show that clustering using the Self Organizing Maps (SOM) method provides better results than using the K-Means clustering method where the DBI value is 0.1829366. The clustering results using the Self Organizing Maps (SOM) method for cluster 1 consist of 31 province members, cluster 2 consists of 1 province member and cluster 3 consists of 2 province members.

Log Linier Binomial Negatif dalam Memodelkan Data Siswa Putus Sekolah Tingkat SMA/SMK

2024-01-11T10:10:54+07:00

Log linear negative binomial model is an extension of the linear regression model that can be used to analyze count data in the form of a contingency table when dealing with overdispersion where the variance value is greater than the mean value. Research in the field of education often produces contingency table data, one of which is data on students dropping out of school. The 2018 BPS survey showed that the number of students dropping out of school at the secondary school level in West Java province had the highest number of dropouts. Unfortunately, quantitative research on dropout students is still rarely done. Log linear negative binomial model is applied to determine the factors that influence the number of SMA/SMK dropout students in West Java province in 2021. The results show that gender, type of middle school, school status, interaction of gender and school status, and the interaction of middle school type and school status significantly affects the number of students dropping out of school. Furthermore, SMA/SMK dropouts in the province of West Java are dominated by male students, vocational students, and public-school students. Females are 1% more risky to drop out than males in public schools, while males are 1% more risky to drop out than females in private schools. SMA students are 59% more risky to drop out than SMK students in public schools, while SMK students are 71% more risky to drop out than SMA students in private school.

Bagan Kendali Variansi dengan Penambahan Variabel pada Nilai Ekspor dan Berat Ekspor

2024-01-18T13:52:21+07:00

To create products or services that meet certain quality standards, supervision and control need to be carried out. Quality control monitors changes in the level of variability, or the level of average, or both to observe changes that occur during the production process. The monitoring stage begins with controlling variability, followed by controlling the average level. Walter A. Shewhart (1920) introduced several variability control charts, including the S² variance control chart, which involves one quality characteristic, Y. Riaz (2008) introduced a regression-type estimator of the variance of Y using additional correlated information X. This control chart is known as the V_r control chart and shows better results than the S² control chart. Furthermore, Riaz (2009) introduced a V_t control chart, created based on a ratio-type estimator of the variance of Y. The accuracy of the V_t control chart increases as the value increases. The S², V_r, V_t control chart is used to monitor the variability of export value (Y) using additional information on export weight (X). All three charts indicate that the variability in export values is out of control. Comparison of the results obtained from the V_t, V_r, and S² control charts is made by examining the power curve of each chart. Specifically, it was observed that the V_t control chart produces more consistent and accurate conclusions.

Regresi Nonparametrik Spline Truncated untuk Memodelkan Tingkat Pengangguran Terbuka di Pulau Kalimantan

2024-01-09T03:43:50+07:00

Nonparametric regression is a statistical technique employed to discern the relationship pattern between a predictor variable and a response variable in the absence of prior information about the form of the regression function or when the pattern of the regression curve is unknown. Truncated spline nonparametric regression represents an approach for aligning data, considering the curve's smoothness. It possesses continuous segmented characteristics, offering flexibility and adeptly accommodating the explanation of local data function features. The study aims to identify the influencing factors on the open unemployment rate in Kalimantan Island during 2020. Additionally, it seeks to derive a spline truncated nonparametric regression model for Open Unemployment Rate data in Kalimantan Island for the same year. The study employs a nonparametric regression model with a spline truncated method, determining optimal knot points based on the minimum Generalized Cross Validation (GCV) value. The study reveals that the most effective spline truncated nonparametric regression model features two knot points. Significant factors influencing the open unemployment rate include the labor force participation rate, school year expectations, regional gross domestic product at current prices, and the human development index.

Analisis Faktor Konfirmatori untuk Mengidentifikasi Peubah Indikator Utama dalam Pengukuran Peubah Laten

2024-01-11T10:12:29+07:00

Research on attitudes, preferences and behavior are research that involves latent variables. Latent variables are measured by observing some indicator variables. Indicator variables that measure a latent variable are selected based on the researcher's perspective, however, it is necessary to consider the previous of related research. Indicator variables need to have theoretical meaning, be valid and reliable in measuring latent variables. Confirmatory factor analysis (CFA) is a statistical method that can be used to determine the validity of the indicator variables. In this research, CFA is used to determine the main indicator variables that characterize the reasons for choosing a study program at a university by high school graduates (or equivalent). There are 20 indicator variables chosen to represent several latent factors such as image, job prospects, interests and campus facilities. The results indicate that the latent factors of image, job prospects, interest and facilities can be respectively represented by the majority of alumni occupying strategic positions in their careers, the easiness of alumni for getting a job, a large number of individuals in surroundings who are working as a data analysts and representative library. The findings also reveals that all the selected indicators are significant so that no indicators need to be excluded. Evaluation of the model shows that the specified model fits the analyzed data. This is indicated by the Comparative Fit Index (CFI), Root Mean Square Error of Approximation (RMSEA), and Standardized Root Mean Square Residual (SRMR) values which reach good fit criteria.