Measures of Goodness of Fit for the Multidimensional Semiparametric Density Ratio Model

• Activity Number: 244
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Section on Nonparametric Statistics
• Author(s): Anastasia Voulgaraki*+ and Benjamin Kedem
• Companies: University of Maryland and University of Maryland
• Keywords: semi parametric density ratio model ; measures of goodness of fit ; regression ; empirical likelihood

Abstract

Suppose we have m multidimensional data sets. Then it is possible to approach regression analysis with random covariates from a semi parametric perspective, where information is combined from multiple multivariate sources and where multivariate distributions are "regressed" on a reference distribution. This approach has the advantage that one does not have to make any specific assumptions regarding the distribution of the data. We also discuss several measures of goodness of fit and diagnostic methods that can be used to check the validity of the model. The method is applied to both simulated and real (cancer) data sets and a comparison with multiple regression is presented.