"Everything should be made as simple as possible, but not simpler." - Albert Einstein

Seminar Announcement

Statistical inference for semiparametric regression models based on the Fourier transforms.

Myriam Vimond, ENSAI (France).

Wednesday, May 6, 2009

3:00 pm, 223 Weber

Abstract: We focus on estimating the deformations that may exist between similar signals or images in the presence of additive noise when a reference template is unknown. The deformations are modeled as parameters lying in a finite dimensional compact Lie group. A general matching criterion based on the Fourier transform and its well known shift property is introduced. M-estimation and semiparametric theory are then used to study the consistency and asymptotic normality of resulting estimators. The method is illustrated by the case where the signals differing from each other by both phases and amplitude. In this case, the method provides us asymptotically efficient estimators.