TY  - THES
N1  - Pembimbing : 1. Dr. Epha Diana Supandi, M.Sc;  2. Malahayati, M.Sc
ID  - digilib44038
UR  - https://digilib.uin-suka.ac.id/id/eprint/44038/
A1  - Astika Riawan Putri, NIM.: 16610036
Y1  - 2020/11/03/
N2  - Linear regression analysis is a technique in statistics used to form model the relationship between the dependent variable with one or more independent variables. The method used to estimate parameters in regression analysis is Ordinary Least Square. Data processing often containing outliers which may have a major effect on the regression coefficient. One method used when data contains outlier is by the robust regression method. In this study, the robust regression used is Least Median Square method. The principle of this method is to minimize the residual median squared. This study aims to detect outliers in the data and compare the effectiveness of the Ordinary Least Square (OLS) and Least Median Square (LMS) methods in forming a regression model. Comparison of this method in terms of AIC and BIC value. The method that has smaller the AIC and BIC value, its meaning that the method is more effective in dealing with outliers. The case studies in this research are the number of unemployment, population density, minimum wages, number of job seekers, and job vacancies based on district/city, which were obtained through the website of Central Java Province BPS in 2018. The results of this study show that the Ordinary Least Square (OLS) method is more effective than the robust Least Median Square (LMS) method in overcoming outliers in the number of unemployed data in Central Java Province in 2018.
PB  - UIN SUNAN KALIJAGA YOGYAKARTA
KW  - Linear Regression Analysis
KW  -  Ordinary Least Square
KW  -  Least Median Square
KW  -  outliers
M1  - skripsi
TI  - ANALISIS REGRESI ROBUST DENGAN METODE
LEAST MEDIAN SQUARE
(Studi Kasus : Jumlah Pengangguran di Provinsi Jawa Tengah Tahun 2018)
AV  - restricted
EP  - 132
ER  -