ANALISIS REGRESI RIDGE GENERALIZED LEAST SQUARE (RGLS) UNTUK MENGATASI MULTIKOLINEARITAS DAN AUTOKORELASI

SHERLINA YULIANTI , sherlinay65@gmail.com (2023) ANALISIS REGRESI RIDGE GENERALIZED LEAST SQUARE (RGLS) UNTUK MENGATASI MULTIKOLINEARITAS DAN AUTOKORELASI. FAKULTAS PERTANIAN , UNIVERSITAS LAMPUNG. (Submitted)

Preview	Text ABSTRAK.pdf Download (264kB) | Preview
	Text SKRIPSI FULL.pdf Restricted to Repository staff only Download (1MB)
Preview	Text SKRIPSI TANPA BAB PEMBAHASAN.pdf Download (1MB) | Preview

Abstract

ABSTRACT RIDGE GENERALIZED LEAST SQUARE (RGLS) REGRESSION ANALYSIS TO OVERCOME MULTICOLLINEARITY AND AUTOCORRELATION By Sherlina Yulianti Multiple linear regression analysis is a method for analyzing the relationship between the dependent variable and several independent variables. The independent variables in multiple linear regression analysis have a possibility to correlate with each other or called multicollinearity problems and linear regression using time series data has a possibility to have error autocorrelation problems because the data at this time has a relationship with data at the previous time. Both of these conditions have an adverse effect on estimates and predictions. The Ridge Generalized Least Square (RGLS) method is able to overcome multicollinearity and autocorrelation problems simultaneously. Therefore this study aims to study the performance of the RGLS method in overcoming multicollinearity and autocorrelation problems through Monte Carlo simulations with n = 50, 75, and 100 which have 6 independent variables with a multicollinearity level of 0.99 and an autocorrelation level of 0.15. This study gives the result that the RGLS method is able to overcome multicollinearity and autocorrelation problems in the data and it can be concluded that the more the number of samples used, the smaller the resulting MSE value and the greater the resulting

Item Type:	Other
Subjects:	?? 000 ?? ?? 001 ??
Divisions:	Fakultas MIPA > Prodi Matematika
Depositing User:	2301484122 . Digilib
Date Deposited:	17 Feb 2023 07:53
Last Modified:	17 Feb 2023 07:53
URI:	http://digilib.unila.ac.id/id/eprint/69534

Actions (login required)

View Item