<html>
<br>
Dear friends.<br>
I believe this problem has been discussed in various forms now and then,
so I hope you will forgive me I ask how to do a truncated model like
this, where the observed y is recorded as 10 whenever it is higher or
equal to that value<br><br>
x <- rnorm(1000)<br>
y <- 10*x + rnorm(1000)<br>
y[which(y>10)] <- 10<br>
and recover the "true" model ?<br><br>
<br>
Best wishes<br>
Troels<br><br>
<x-sigsep><p></x-sigsep>
Troels Ring, MD<br>
Department of Nephrology<br>
Aalborg Hospital, Denmark<br>
<font color="#0000FF"><b><i>tring@gvdnet.dk<br>
</i></b></font>fax 00 45 99 32 22 34<br>
tlf 00 45 99 32 22 42<br>
00 45 98 14 05 82 (home)</html>