Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : ARRUS Journal of Mathematics and Applied Science

Ordinary Least Square Method in Multiple Regression Analysis to Estimating Coefficients of Factors Affecting Human Development Index Suhendra, Ogi; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 1 (2022)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience632

Abstract

Analisis Regresi merupakan suatu analisis data yang memperhatikan hubungan antara suatu peubah respon (response variable) dengan satu atau lebih peubah penjelas (explanatory variables). Penelitian ini menggunakan metode Ordinari Least Square (OLS). Metode OLS merupkan metode dasar yang digunakan untuk menyelesaikan suatu masalah data dengan penyelesaian berbentuk model regresi linier. Hasil pemodelan menunjukkan pengaruh variabel Angka Harapan Hidup, Harapan Lama Sekolah, Rata-Rata Lama Sekolah, dan Pengeluaran Perkapita terhadap Indeks Pembangunan Manusia Provinsi Sulawesi Selatan dilihat dari nilai R-Square sebesar 99.63%. menunjukkan bahwa besar persentase variasi Indeks Pembangunan Manusia yang bisa dijelaskan oleh keempat variabel bebas yaitu Angka Harapan Hidup, Harapan Lama Sekolah, Rata-rata Lama Sekolah, dan Pengeluaran Perkapita, sebesar 99.63% sedangkan sisanya sebesar 0.37 dijelaskan oleh variabel-variabel lain diluar penelitian. Artinya semua variabel bebas berpengaruh signifikan terhadap variabel terikat dengan taraf signifikan 5%.
Development of R Package for Regression Analysis with User Friendly Interface Amir, Arfan Shalihin; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 1 (2022)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience728

Abstract

The use of pirated software in Indonesia is quite high compared to other countries in the world. One of the efforts made to reduce the level of software piracy is to develop publicly licensed software such as R software which is open source software. The preparation of this package uses the R software and other additional packages, especially packages for regression analysis. Making this package can make it easier for users to perform regression analysis easily and legally. This package is named SLR App (Simple Linear Regression App) and MLR App (Multiple Linear Regression) which are regression analysis packages that have a user friendly interface. From the tests carried out that this package has similarities from the results of the analysis between the SLR App and MLR App.
Spatial Regression Analysis to See Factors Affecting Food Security at District Level in South Sulawesi Province Safitri, Irma Yani; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 2 (2022)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience740

Abstract

Spatial regression is a development of classical linear regression which is based on the influence of place or location. To determine the location/spatial effect, a spatial dependency test was performed using the Moran Index, and the Lagrange Multiplier (LM) test was used to determine a significant spatial regression model. In this study, spatial regression was applied to the case of food security in each district in South Sulawesi Province. The results of the analysis show that there is a negative spatial autocorrelation, meaning that the spatial effect does not affect the level of food security. The significant spatial regression model is the SEM (Spatial Error Model) model. The equation of the SEM model produces variables that have a significant effect, namely the ratio of normative consumption per capita to net availability, percentage of population living below the poverty line, percentage of households with a proportion of expenditure on food more than 65 percent of total expenditure, percentage of households without access to electricity, percentage of households without access to clean water, life expectancy at birth, ratio of population per health worker to the level of population density, the average length of schooling for women above 15 years, and the percentage of children under five with height below standard (stunting). Thus, the resulting distribution pattern is a uniform data pattern. This means that each adjacent district tends to have different characteristics.
Comparison of k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) Methods for Classification of Poverty Data in Papua Fauziah; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 2 (2022)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience741

Abstract

Classification is a job of assessing data objects to include them in a particular class from a number of available classes. The classification method used is the k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) methods. The data used in this study is data on poverty in Papua with the category of the number of low/high level poor people. Of the 29 regencies/cities that were sampled, 15 regencies/cities represent the number of low-level poor people and 14 districts/cities are the number of high-level poor people. The results of the analysis obtained are the k-Nearest Neighbor (k-NN) method with a value of k=15 producing an accuracy of 58.62%, while the Support Vector Machine (SVM) method with Parameter cost = 1 using the RBF kernel produces an accuracy value. by 93.1%. The classification criteria to find the best method is to look at the Root Mean Square Error (RMSE) which states that the Support Vector Machine (SVM) method is better than the k-Nearest Neighbor (k-NN) method.
Spatial Regression Analysis to See Factors Affecting Food Security at District Level in South Sulawesi Province Safitri, Irma Yani; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 2 (2022)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience740

Abstract

Spatial regression is a development of classical linear regression which is based on the influence of place or location. To determine the location/spatial effect, a spatial dependency test was performed using the Moran Index, and the Lagrange Multiplier (LM) test was used to determine a significant spatial regression model. In this study, spatial regression was applied to the case of food security in each district in South Sulawesi Province. The results of the analysis show that there is a negative spatial autocorrelation, meaning that the spatial effect does not affect the level of food security. The significant spatial regression model is the SEM (Spatial Error Model) model. The equation of the SEM model produces variables that have a significant effect, namely the ratio of normative consumption per capita to net availability, percentage of population living below the poverty line, percentage of households with a proportion of expenditure on food more than 65 percent of total expenditure, percentage of households without access to electricity, percentage of households without access to clean water, life expectancy at birth, ratio of population per health worker to the level of population density, the average length of schooling for women above 15 years, and the percentage of children under five with height below standard (stunting). Thus, the resulting distribution pattern is a uniform data pattern. This means that each adjacent district tends to have different characteristics.
Comparison of k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) Methods for Classification of Poverty Data in Papua Fauziah; Tiro, Muhammad Arif; Ruliana
ARRUS Journal of Mathematics and Applied Science Vol. 2 No. 2 (2022)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience741

Abstract

Classification is a job of assessing data objects to include them in a particular class from a number of available classes. The classification method used is the k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) methods. The data used in this study is data on poverty in Papua with the category of the number of low/high level poor people. Of the 29 regencies/cities that were sampled, 15 regencies/cities represent the number of low-level poor people and 14 districts/cities are the number of high-level poor people. The results of the analysis obtained are the k-Nearest Neighbor (k-NN) method with a value of k=15 producing an accuracy of 58.62%, while the Support Vector Machine (SVM) method with Parameter cost = 1 using the RBF kernel produces an accuracy value. by 93.1%. The classification criteria to find the best method is to look at the Root Mean Square Error (RMSE) which states that the Support Vector Machine (SVM) method is better than the k-Nearest Neighbor (k-NN) method.