Xplore: Journal of Statistics 2021-01-01T16:20:07+07:00 Akbar Rizki, S.Si, M.Si Open Journal Systems <p><strong>Xplore: <em>Journal of Statistics</em>&nbsp;</strong>diterbitkan berkala 3 (tiga) kali dalam setahun yang&nbsp;memuat tulisan ilmiah yang berhubungan dengan bidang statistika.&nbsp; Artikel yang dimuat berupa hasil penelitian atau kajian pustaka dalam bidang statistika dan atau penerapannya.</p> <p><a href="" target="_blank" rel="noopener">ISSN:&nbsp;2302-5751.</a></p> <p>Mulai Desember 2018, Xplore: Journal of Statistics mendapatkan ISSN baru untuk media online (eISSN:2655-2744) sesuai dengan SK no. 0005.26552744/JI.3.1/SK.ISSN/2018.12 - 13 Desember 2018. Maka sesuai ketentuan pada SK tersebut, edisi Xplore: Journal of Statistics mulai Desember 2018 akan dimulai menjadi Volume 7 dan No 3.&nbsp;&nbsp;</p> <p><a href="" target="_blank" rel="noopener">eISSN:&nbsp;2655-2744</a></p> Pemodelan Pola Produktivitas Cabai Rawit di Kabupaten Magelang 2019-07-10T09:28:44+07:00 Yohanes Purnama Farit M Affendi Agus M Soleh <p>The objective of this study was to determine the best model that describe the pattern of cayenne pepper productivity in Magelang Regency. This study uses primary data which was obtained from the results of a survey of cayenne pepper production by the General Director of Horticulture on several sample plots in Magelang District, Central Java Province in 2018. The process of data analysis was divided into two parts: grouping the sample plots based on the similarity in productivity pattern and then fitting models in each group. The models used to fit data were Logistic Growth Model, Monomolecular Growth Model, Exponential Growth Model, Polynomial Model and Linear B-Spline Model. The best model was determined based on R<sup>2</sup> and MAPE. The results showed that the pattern of cayenne pepper productivity in Magelang District had eight different characteristics. Characteristics of each groups were illustrated by the similarity of their productivity pattern. The best model in each group was B-Spline Linear Model.</p> <p>&nbsp;</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Two step Cluster Application to Classify Villages in Kabupaten Madiun Based on Village Potential Data 2019-04-02T03:26:45+07:00 Alif Supandi Asep Saefuddin Itasia Dina Sulvianti <p>Village development is a fundamental part of national development. Developing villages requires information on society necessities. This research aims at clustering villages in <em>Kabupaten Madiun</em> which has similar characteristics among each other and identify characteristics of the built clusters. Therefore, specific problems in the clusters of villages may become the foundation to implement development. The method that used for grouping objects with combined variables is two-step cluster. This analysis was used 14 variables consist of six categorical variables and eight numerical variables. The clustering analysis produces four clusters. The clusters that need more attention to be developed was Cluster 2 which had minimum facilities and resources. The average Silhouette coefficient for the clusters built was 0.3 which can be considered as fair category.</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Metode Alternatif dalam Pencarian Peringkat E-Commerce di Indonesia Berdasarkan Rating Pelanggan 2019-05-11T23:20:10+07:00 Azira Irawan Aam Alamudi Septian Rahardiantoro <p>The existence of the internet raises an online trading system using applications. The rise of online trading systems has triggered the emergence of various e-commerce in Indonesia that provide various kinds of customer needs. This also causes problems for customers, namely the difficulty in choosing quality e-commerce. The effort to overcome this problem is to rank e-commerce in Indonesia based on customer ratings. The method commonly used for ranking is the analytical hierarchy process (AHP) method, but in practice there are several variables that are not found in e-commerce so the AHP method cannot be used. The alternative method chosen is the ant colony optimization (ACO) method. The feasibility test of the ACO method in searching rankings for e-commerce data needs to be done because not all variables are in e-commerce. Simulations for ranking search are carried out using 2 generated data scenario with analytical hierarchy process (AHP) and ant colony optimization (ACO) method. The simulation results show that the ACO method is feasible to be used for ranking with blank data, then the application of the ACO method for e-commerce data in Indonesia. The best taboo results are based on the highest opportunity value and the highest correlation coefficient, namely in the second taboo, with three major ratings, namely JD, SP, and TP</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Penggerombolan Hasil Ujian Nasional Menggunakan K-Rataan Samar 2019-07-09T04:40:09+07:00 Nouval Habibie Akbar Rizki Pika Silvianti <p>National examination scores can be a basis for the government to make a mapping of education quality in order to increase it. The mapping can be done by using fuzzy cluster analysis. The objective of this experiment is to cluster districts/cities in Indonesia based on national examination score in natural and social science in 2014/2015 until 2017/2018 school year by using the fuzzy c-means method. The evaluation criteria that will be used are the standard deviation ratio, silhouette coefficient, and Xie Beni index. The best cluster size is two clusters, A and B. The clustering result shows cluster A has a higher mean from each subject than cluster B. Therefore, cluster A will be categorized as good, whereas cluster B as bad. The proportion of districts/cities that belong to cluster A decreased each year. The final cluster result can be determined by the mean of its degree of membership from those four school years. The analysis results show that the distribution of education quality is dominated in Java Island and squatter cities. East Nusa Tenggara, West Sulawesi, Central Sulawesi, and North Kalimantan don’t have any districts/cities belong to cluster A.</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Seleksi Peubah menggunakan Algoritme Genetika pada Data Rancangan Faktorial Pecahan Lewat Jenuh Dua Taraf 2019-07-17T16:33:30+07:00 Ani Safitri Rahma Anisa Bagus Sartono <p>In certain fields, experiments involve many factors and are constrained by costs. Reducing runs is one of the solutions to reduce experiment costs. But that can cause the number of runs to become less than the number of factors. This case of experimental design also is known as a supersaturated design. The important factors in this design are generally estimated by involving variable selection such as forward selection, stepwise regression, and penalized regression. Genetic algorithm is one of the methods that can be used for variable selection, especially for high dimensional data or supersaturated design. This study aims to use a genetic algorithm for variable selection in the supersaturated design and compare the genetic algorithm results with a stepwise regression which is generally used for a simple design. This study also involved fractional factorial design principles. The result showed that the main factors and interactions of the genetic algorithm and stepwise regression were quite different. But the principle was the same because the variables correlated. The genetic algorithm model had a smaller AIC and BIC and all of the main factors and interactions which had chosen were significant on the 0.1%. Therefore genetic algorithm model was chosen although computation time was much longer than stepwise regression.</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Pengaruh Karakteristik Pasien 4 Diagnosis Penyakit Rawat Inap dengan Biaya Tertinggi di PT Asuransi ABC Terhadap Biaya Rawat Inap Berdasarkan Data Klaim 2020-12-11T02:37:49+07:00 Saskya Mary Soemartojo Titin Siswantining Darayani Putri Mariam Rahmania <p>PT Asuransi ABC in collaboration with 68 companies, consists of 34960 participants, of which there are 1731 participants who filed claims. This study uses secondary data period July 1, 2013 - 30 September 2014. This study focused on inpatient claims, where there are 4 burdensome disease diagnosis PT Asuransi ABC at a high cost, those are coronary atrial diseases, chronic renal failure, typhoid fever, dengue haemorrhagic fever. Multiple correspondence analysis method is used to find the characteristics of each patient's disease diagnosis as well as the tendency of the characteristics of the patients in the cost of hospitalization . From the research, there are differences in patient characteristics between the disease and also the trend in the cost of hospitalization . Furthermore, the multiple linear regression analysis of patient characteristics influence on the cost of hospitalization . From the results of research only typhoid disease hospitalization costs are influenced by patient characteristics .</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2020 Xplore: Journal of Statistics Identifikasi Faktor-Faktor yang Memengaruhi Prestasi Mahasiswa Menggunakan Regresi Logistik Ordinal dan Random Forest Ordinal 2021-01-01T16:20:07+07:00 Zuhdiyah Izzatun Nisa' Agus M Soleh Hari Wijayanto <p>Student achievement is the result of student learning processes and efforts. This research was conducted through a survey of students of the 2015-2017 FMIPA IPB with the selection of respondents using stratified random sampling. The purpose of this study is to identify the factors that influence the achievements of the 2015-2017 FMIPA IPB students using ordinal logistic regression and ordinal random forest. The response variable used is the PPKU GPA category and the last even semester GPA which is categorized based on the predicate of IPB graduation. The results of ordinal logistic regression get 7 explanatory variables that influence the PPKU GPA and 7 explanatory variables that influence the last even semester GPA. Explanatory variables that have a significant effect on ordinal logistic regression and become 10 variables with the highest level of importance in the ordinal random forest for both response variables are department, mother’s education, internet access in a day for games, activity in the class, and active work on a group assignment.</p> 2021-01-01T00:00:00+07:00 Copyright (c) 2021 Xplore: Journal of Statistics