Adaptive robust regression with continuous Gaussian scale mixture errors

Byungtae Seo, Jungsik Noh, Taewook Lee, Young Joo Yoon

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

Model based regression analysis always requires a certain choice of models which typically specifies the behavior of regression errors. The normal distribution is the most common choice for this purpose, but the estimator under normality is known to be too sensitive to outliers. As an alternative, heavy tailed distributions such as t distributions have been suggested. Though this choice can reduce the sensitivity to outliers, it also requires the choice of distributions and tuning parameters for practical use. In this paper, we propose a class of continuous Gaussian scale mixtures for the error distribution that contains most symmetric unimodal probability distributions including normal, t, Laplace, and stable distributions. With this quite flexible class of error distributions, we provide the asymptotic property and robust property of the proposed method, and show its successes along with numerical examples.

Original languageEnglish (US)
Pages (from-to)113-125
Number of pages13
JournalJournal of the Korean Statistical Society
Volume46
Issue number1
DOIs
StatePublished - Mar 1 2017

Keywords

  • Adaptive robust regression
  • Asymptotics
  • Continuous scale Gaussian mixture
  • M-estimation

ASJC Scopus subject areas

  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Adaptive robust regression with continuous Gaussian scale mixture errors'. Together they form a unique fingerprint.

Cite this