\HeaderA{nwtco}{Data from the National Wilm's Tumor Study}{nwtco}
\keyword{datasets}{nwtco}
\begin{Description}\relax
Missing data/masurement error example. Tumor histology predicts
survival, but prediction is stronger with central lab histology than
with the local institution determination.
\end{Description}
\begin{Usage}
\begin{verbatim}data(nwtco)\end{verbatim}
\end{Usage}
\begin{Format}\relax
A data frame with 4028 observations on the following 9 variables.
\describe{
\item[\code{seqno}] id number
\item[\code{instit}] Histology from local institution
\item[\code{histol}] Histology from central lab
\item[\code{stage}] Disease stage
\item[\code{study}] study
\item[\code{rel}] indicator for relapse
\item[\code{edrel}] time to relapse
\item[\code{age}] age in months
\item[\code{in.subcohort}] Included in the subcohort for the example in the
paper
}
\end{Format}
\begin{Source}\relax
\url{http://faculty.washington.edu/norm/software.html}
\end{Source}
\begin{References}\relax
N.E. Breslow and N. Chatterjee, "Design and analysis of two-phase studies with binary outcome applied to Wilms tumour prognosis"  Applied Statistics  48:457-68, 1999
\end{References}
\begin{Examples}
\begin{ExampleCode}
data(nwtco)
with(nwtco, table(instit,histol))
anova(coxph(Surv(edrel,rel)~histol+instit,data=nwtco))
anova(coxph(Surv(edrel,rel)~instit+histol,data=nwtco))
  \end{ExampleCode}
\end{Examples}