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: survival analysis with time varying covariates

From   "D.W.Richards" <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: st: survival analysis with time varying covariates
Date   Wed, 3 Aug 2011 09:23:29 +0100

Hi Meg,

I recommend reading the survival analysis book.  It explains two ways of structuring your data to deal with TVCs.  Here is the link.

I used it for my TVCS and it worked well.


From: Austin Nichols [[email protected]]
Sent: 02 August 2011 20:45
To: [email protected]
Subject: Re: st: survival analysis with time varying covariates

mosterbur <[email protected]>:
All of the data is measured annually?
Consider shifting to a discrete-time model; see

On Tue, Aug 2, 2011 at 3:06 PM, mosterbur <[email protected]> wrote:
> I'm working on project using survival analysis to predict policy adoption and
> I am having trouble with how to handle to my time varying covariates(TVCs).
> My dataset is annual data for 35 countries from 1971 to 2005 and includes
> variables for inflation, education expenditures, gdp, etc all of which vary
> annually. Everything that I have read has indicated that for TVCs I need to
> use stsplit to split my data, but this seems problematic given that I would
> need to split the data for every year for every country.
> Can anyone explain to me how I can appropriately handle the TVCs?
*   For searches and help try:

The Open University is incorporated by Royal Charter (RC 000391), an exempt charity in England & Wales and a charity registered in Scotland (SC 038302).

*   For searches and help try:

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