\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, April 4, 2000}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Guenther Walther}
\centerline{\sl Department of Statistics}
\centerline{\sl Stanford University}
\bigskip
\centerline{\bf Estimating the number of components in a mixture}
\bigskip



Estimating the number of components (`clusters') in a mixture is an
important problem in many applications, but the theory is not well
developed due to various difficulties inherent in the problem. Juxtaposing
the univariate setting with the mutivariate set-up reveals a sharp contrast
that can be exploited to get new insight into problem. We will apply those
lessons to both an approach based on
the empirical measure, and to one based on moment methods (k-means). The
latter part is joint work with Rob Tibshirani.

\bye