Robust Inference in Some Multiple Multifactor Dynamical Systems

• Activity Number: 194
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: SSC
• Author(s): Sévérien Nkurunziza*+
• Companies: University of Windsor
• Keywords: Asymptotic distributional risk ; Diffusion process ; MLE ; Shrinkage estimator ; Wiener process

Abstract

In this paper, we are interested in estimation problem concerning the drift parameters matrices of $m$ independent multivariate diffusion processes. More specifically, we consider the case where the $m$-parameters matrices are suspected to satisfy some restrictions. Given such an uncertainty, we develop shrinkage estimators which improve over the performance of the maximum likelihood estimator (MLE). Under an asymptotic distributional quadratic risk criterion, we study the relative dominance of the established estimators. Further, we carry out intensive simulation studies for observation periods of small and moderate lengths of time that illustrate the performance of the proposed method. Simulation results corroborate the theoretical finding for which shrinkage estimators outperform over the MLE. The proposed method is useful in model assessment and variable selection.