\documentclass[11pt]{article}
\setlength{\oddsidemargin}{0.0truein}
\setlength{\evensidemargin}{0.0truein}
\setlength{\textwidth}{6.5truein}
\setlength{\topmargin}{0.0truein}
\setlength{\textheight}{9.0truein}
\setlength{\headsep}{0.0truein}
\setlength{\headheight}{0.0truein}
\setlength{\topskip}{10.0pt}
\usepackage{url}
\begin{document}
\begin{center}
  \textbf{\textsc{STANFORD UNIVERSITY}}\\[5pt]
  \textbf{\textsc{DEPARTMENT OF STATISTICS}}\\[5pt]
  \Large{\textbf\textsc{{DEPARTMENTAL SEMINAR}}}
\end{center}
\begin{center}
  4:15 p.m., Tuesday, May 24, 2005\\
  Sequoia Hall Room 200\\
  (Cookies at 3:45 in 1st Floor Lounge)
\end{center}

\begin{center}
  \textsl{Gary Lorden}\\
  Department of Mathematics\\
  Caltech\\
\end{center}
\begin{center}
  \textbf{Some Optimal Fixed-shape Confidence Intervals}
\end{center}

Abstract.  It might seem that nothing new could be said about
constructing confidence intervals for the one-dimensional parameter of
a common discrete distribution like the binomial, hypergeometric or
Poisson.  But a lawyer's question-"What's the smallest sample size
that will give a margin of error less than 10\% for the percentage
defective in this population?" -- led to a method for constructing
efficient confidence intervals, one that appears particularly useful
in multistage sampling.

\end{document}