\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, October 16, 2001}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Andreas Futschik}
\centerline{\sl Department of Statistics}
\centerline{\sl University of Vienna}
\bigskip
\centerline{\bf Subsampling of Biased Statistics with application to the identification of locations of extremal 
points}

\bigskip

We consider the application of bootstrap and subsampling to roots that
involve biased statistics. A situation where such statistics frequently
occur, is in nonparametric estimation and testing problems. Bootstrap
usually fails in this context, since the bias is not approximated
consistently. Subsampling, however often works. We investigate conditions
under which subsampling works with biased statistics and consider
applications both where the bias converges and diverges. We investigate in
particular a statistic that is useful for identifying points where density
and intensity functions achieve a maximum and for which the renormalized
bias diverges. We apply this statistic to ship arrival data.


\bye