\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, November 20, 2001}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Lutz Duembgen}
\centerline{\sl Medical University}
\centerline{\sl Luebeck, Germany}
\bigskip
\centerline{\bf Nonparametric Analysis of Interval-Censored Data}

\bigskip

Suppose that we want to estimate an unknown distribution function $F$ on
$(0,\infty]$. Instead of observing a random sample $X_1,\ldots,X_n$ from $F$,
for each unit $i$ we only know an interval $(L_i,R_i]$ containing the event
time $X_i$. This talk presents nonparametric estimators for $F$ (a) without
further restrictions, (b) assuming it to be concave, and (c) assuming it to
be unimodal.  Consistency properties as well as computational aspects are
treated. 

\bye