Robust Ridge regression to solve a multicollinearity and outlier

N. E. Jeremia, S. Nurrohmah, I. Fithriani

Research output: Contribution to journalConference articlepeer-review

Abstract

Regression analysis is one of many methods used for analysing data. Method that used for estimating parameter in linear regression model is ordinary least square (OLS). OLS will give best estimator when all the assumptions are met. But in reality, sometimes not all the assumptions are met. Assumptions that usually violated are multicollinearity and outlier. Ridge regression is a regression method that give constrain on the parameters that used to deal with multicollinearity, meanwhile Robust regression is used to overcome the presence of outlier. Robust regression is a regression method that has robust property that achieved by using S-estimation is used. Ridge regression and Robust regression combined into Robust Ridge regression to overcome multicollinearity and outlier simultaneously.

Original languageEnglish
Article number012030
JournalJournal of Physics: Conference Series
Volume1442
Issue number1
DOIs
Publication statusPublished - 29 Jan 2020
EventBasic and Applied Sciences Interdisciplinary Conference 2017, BASIC 2017 - , Indonesia
Duration: 18 Aug 201719 Aug 2017

Keywords

  • multicollinearity
  • outlier
  • regression
  • Ridge
  • Robust

Fingerprint Dive into the research topics of 'Robust Ridge regression to solve a multicollinearity and outlier'. Together they form a unique fingerprint.

Cite this