\magnification=1200
\baselineskip=20pt
\nopagenumbers
\font\big=cmr12 scaled \magstep2

\centerline{\bf STANFORD UNIVERSITY}
\centerline{\bf DEPARTMENT OF STATISTICS}
\centerline{\big DEPARTMENTAL SEMINAR}
\bigskip

\baselineskip=12pt
\centerline{4:15 p.m., Tuesday, February 29, 2000 }
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 p.m. in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Christiane Lemieux}
\centerline{\sl Department of Statistics}
\centerline{\sl Stanford University}
\bigskip
\centerline{\bf Variance Reduction via Lattice Rules}
\centerline{\bf }
\bigskip

Quasi-Monte Carlo methods are designed to improve upon the Monte Carlo
method for multidimensional numerical integration by replacing the i.i.d.\
sample by a more regularly distributed point set. Lattice rules are one
family of quasi-Monte Carlo methods, proposed by Korobov in 1959. In this
talk, we study
how randomized lattice rules can be used to construct efficient estimators
for problems where simulation is typically used. We are mainly interested
in studying the variance of these estimators, and in proposing selection
criteria for lattice rules that pay attention to the low-dimensional
structure of the lattice. 

Joint work with Pierre L'Ecuyer, Departement IRO, Universite de Montreal,
(Computer Science and Operations Research Department) 

\bye