Boris Levit


Professor

Office: Jeffery Hall, Rm. 511
Phone: (613) 533-2439
Email: blevit@queensu.ca
Website:
Research: Optimal design in non-parametric regression

Degrees & Accolades:

Ph.D. (Institute of Information Transmission, Moscow)
Dr.Sc. (Vilnius University)

Research Profile:

For many decades problems of optimal estimation in Statistics were solved primarily in the asymptotic setting, i.e., under the assumption that the number of available statistical observations was large. A more modern approach is to study such problems in a non-asymptotic setting, when the number of observations is moderate or small.

In the non-parametric regression problems such approach is based on the use of the Jacobi elliptic functions well known in classical Analysis, Number Theory, and Communication Theory. Some problems in this direction have been solved recently, but many open questions remain just waiting to be investigated.

I am currently recruiting graduate students.