%0 Thesis
%9 Skripsi
%A Reviana Astuti, NIM.: 18106010012
%B FAKULTAS SAINS DAN TEKNOLOGI
%D 2022
%F digilib:56130
%I UIN SUNAN KALIJAGA YOGYAKARTA
%K Robust Regression Analysis; Robust Regression Estimation; Outliers
%P 120
%T ROBUST REGRESSION WITH M, S, AND LTS ESTIMATES IN THE  CASE OF SHARIA STOCKS IN INDONESIA
%U https://digilib.uin-suka.ac.id/id/eprint/56130/
%X Regression analysis is one of the statistical methods used to determine the  effect of the dependent variable on the independent variable. The purpose of the regression  analysis is to obtain a regression parameter estimation model of a data. To  estimate the regression parameters, the Least Squares Method (MKT) or commonly  known as Ordinary Least Square (OLS) can be used. However the OLS method is  not appropriate for data containing outliers or outliers. Thus, the robust regression  estimation method is used. In this research the robust regression model used is the  Least Trimmed Square estimation (LTS), Scale estimation (S), and Maximum Likelihood  Type estimation (M). Research purposes this is to obtain the best model in  forming the parameter estimation model regression by comparing the three robust  regression models on the data. Estimation the best robust regression is the estimation  with the Residual Standard Error (RSE) value and the Smallest Mean Squared  Error (MSE) and the largest Adjusted R-square. Studies the case in this study is Indonesian  sharia shares registered with ISSI period January 2017 - December 2021  with the dependent variable ISSI stock index and the independent variable inflation,  Bank Indonesia Syari’ah Certificates (SBIS), and Gross Domestic Product (GDP).  The results of the case study research on the closing price of Indonesian syari’ah  ham registered with ISSI for the period January 2017 - December 2021 it is found  that the best estimate is the S-estimation with a value of ¯R2 of 0.5482, the RSE  value is 7.899 and the MSE value is 176.5142.
%Z Pembimbing:  Mohammad Farhan Qudratullah, S.Si., M.Si.