Generalized Fiducial Inference for Mixed Linear Models

• Activity Number: 177
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: IMS
• Author(s): Jessi Cisewski*+ and Jan Hannig
• Companies: The University of North Carolina at Chapel Hill and The University of North Carolina at Chapel Hill
• Keywords: generalized fiducial inference ; mixed linear models ; variance components ; sequential Monte Carlo ; sequential importance sampling

Abstract

While linear mixed modeling methods are foundational concepts introduced in any statistical education, adequate methods for estimation involving models with more than a few variance components is lacking, especially in the unbalanced setting. Generalized fiducial inference provides a framework that accommodates this dearth of methodology. Under the fabric of generalized fiducial inference along with sequential Monte Carlo methods, we present an approach for estimation for both balanced and unbalanced Gaussian mixed linear models. This approach applies to situations where the data are measurements with a degree of uncertainty or where the data are intervals. We compare the proposed method to classical results in the literature.