MPS-RR 1999-6
January 1999

Parameter identification for stochastic Burgers flows via parabolic rescaling

by:

Nikolai N. Leonenko, Wojbor A. Woyczynski

Abstract

The paper presents a systematic study of classical statistical inference problems (parameter estimation and hypothesis testing) for random fields arising as solutions of the one-dimensional nonlinear diffusion equation with random initial data (the Burgers turbulence problem). This nonlinear, hydrodynamic-type partial differential equation is an ubiquitous model in physics and engineering. This work can be seen as part of a larger program of developing statistical inference tools for complex stochastic flows governed by nontrivial physically constrained dynamics.

Availability: [ gzipped ps-file ] [ pdf-file ]

[ Help on down-loading/viewing/printing ]

This paper has now been published in Probability and Mathematical Statistics (2001) 21, 1, 1-55.