Year: 2014
Type: article
Abstract: Bayesian methods have proven themselves to be successful across a wide range of scientific problems and have many well-documented advantages over competing methods.However, these methods run into difficulties for two major and prevalent classes of problems: handling data sets with outliers and dealing with model misspecification.This dissertation introduces the restricted likelihood as a solution to these problems.When working with the restricted likelihood, we summarize the data through a set of (insufficient) statistics, targeting inferential quantities of interest, and update the prior distribution with the summary statistics rather than the complete data.By choice of conditioning statistics, we retain the main benefits of Bayesian methods while reducing the sensitivity of the analysis to features of the data not picked up by the conditioning statistics.The method is general, but this dissertation concentrates on applying the restricted likelihood to the common Bayesian linear model when outliers are of concern.For conditioning statistics we mostly consider classical robust M-estimators.In this sense, the method can be viewed as a blend of classical robust estimation techniques with the Bayesian paradigm.Of considerable interest is the comparison of the new method with more traditional approaches to dealing with outliers.In the face of model inadequacy caused by outliers, the traditional view is that one should build a better model which attempts to explain the outlier generating process.Two classical parametric approaches to deal with the problem are to replace the standard density by a thick-tailed or mixture density.Using several It goes without saying that graduate school is hard.My success in the endeavor would not have been possible without the support of many people, some of whom I will no doubt mistakenly fail to mention.My wife, Elise, with whom I make all important life decisions, was nothing but supportive of my idea to pursue my doctorate.Her love and encouragement has continued to keep me grounded and aware of the things that really matter in life.I thank my mother and father for leading by example and always encouraging me in my pursuits.Thanks also to my brother Dan, whom I have always looked up to.Despite his continued jokes about how long I've been in school, I could not have asked for a better older brother.On the academic side, I have to mention that my advisors, Professors MacEachern and Lee, have been the best mentors I could have ever hoped for.I am thankful for their many hours of conversations regarding this work, their thoughtful questions, and helpful suggestions.Their approach to problem solving has helped me out of a countless number of ruts and has been truly enlightening to me.My first statistics course was taught by Dr. Murphree
Author: J. R. Lewis
Institution: The Ohio State University
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2526568247
