\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 24, 2001}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Shripad Tuljapurkar}
\centerline{\sl Department of Biological Sciences}
\centerline{\sl Stanford University}
\centerline{\sl Stanford,  CA 94305}
\bigskip
\centerline{\bf The Stochastic forecast models in demography:  progress 
and problems}

\bigskip

Demographers try to make forecasts of mortality and fertility in order to
forecast population. A surprisingly simple model works well for some human
mortality experience, but has limitations. I will present results from 
this
model (the Lee-Carter model) for the seven rich industrialized countries,
talk briefly about its success, then focus on the problems that remain.
These include --
is there a systematic structure to SVD models; how should one aggregate a
disaggregated model;
how does one properly evaluate a stochastic forecast? I will also talk
briefly about unit root models
for fertility, and discuss related issues in that model. This will be a
talk that aims to ask at least as many questions as it answers.

\bye