\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, March 1, 2005}
\centerline{Sequoia Hall Room 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Andrew Carter}
\centerline{Department of Statistics}
\centerline{UC, Santa Barbara}
\bigskip
\centerline{\bf Goodness of fit tests using asymptotic approximations}
\bigskip

Abstract:

It is well known that estimating an unknown smooth density from  n 
independent observations can be approximated by estimating the mean of a 
continuous Gaussian process.  A transformation of the independent 
observations yields approximately normal increments of a Brownian Motion 
with drift process. As an application of this approximation, I consider 
a simple goodness of fit test. The Gaussian approximation provides a way 
to calculate the level and power of a Kolmogorov--Smirnov type test. 
This test can be compared to a chi-squared test based on binned data 
which is a lieklihood ratio test under restricted conditions.

\bye