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: st :Endogenous variables in Survival analysis

From   Austin Nichols <>
Subject   Re: st: st :Endogenous variables in Survival analysis
Date   Fri, 26 Apr 2013 17:35:45 -0400

Ayman Farahat <>:
There are various approaches e.g.
but no canned package AFAIK.

You can always specify a discrete time hazard model, estimate as a
linear model with time controls, then use -ivreg2-, but there is no
guarantee you will be better off estimating a linear approximation of
the nonlinear model using IV relative to ignoring the endogeneity.

On Fri, Apr 26, 2013 at 5:11 PM, Ayman Farahat <> wrote:
> Hello ;
> I am performing a survival analysis. I suspect that some of my variables are endogenous and i can instrument for them.
> My question is how do i incorporate my instruments in survival analysis using Stat.
> There was a previous post on the list but i was not able to find any responses or followups to the question.
> Best
> Ayman
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index