Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Cox regression, one observation

From   Antoine Terracol <>
Subject   Re: st: Cox regression, one observation
Date   Thu, 13 Jun 2013 23:04:54 +0200

Hi Lee,

what does -stset- report?

Your setting should not be a problem, as illustrated below:

input id t d x
1 1 1 1.5
2 1 0 0.75
3 1 0 2
3 3 1 2.5
stset t, id(id) failure(d)
stcox x

The fisrt 2 cases have one "month", while the second has 3 (and two rows)


On 13/06/13 22:41, Lee Savage wrote:
I am running a survival analysis consisting of a dataset with 73 subjects. My duration time is months and three of my cases have durations of just one month meaning that their observed entry and exit is in the same row of the dataset. These cases are seemingly being excluded from the model as stset for the cases is _t=1 and _t0=0. My question is can I do anything to try and include these cases in the model or does survival analysis require that each case has at least two observations to be included?


*   For searches and help try:

Ce message a ete verifie par MailScanner
pour des virus ou des polluriels et rien de
suspect n'a ete trouve.

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index