Re: st: Time-varying covariates

[Kyleigh Schraeder <kyschraeder@gmail.com>]

Thank you Tom for your helpful advice!

Kyleigh

On Thu, May 10, 2012 at 4:32 PM, Weichle, Thomas <Thomas.Weichle@va.gov> wrote:
> You may want to look into the command -stplit- for creating time-varying
> covariates for discrete data.
>
> Suppose Waiting_Status is a discrete variable with 0 = still waiting, 1
> = received help.  The variable Wait_Time_A is the time from the
> beginning of the study until a person received help.  You would split
> the data at the point in which a person received help.  Prior to this
> point, in the time spectrum, this person had a Waiting_Status value of
> 0.  After this point, this person would have Waiting_Status value of 1
> and would continue to be categorized as 1 until event or censoring.
>
> stsplit Waiting_Status_tvc, at(0) after(time = Wait_Time_A)
> replace Waiting_Status_tvc = Waiting_Status_tvc + 1 if Waiting_Status ==
> 1
>
> Only individuals that received help would be split resulting in multiple
> records for this individual.  Waiting_Status_tvc is the new time-varying
> covariate which is created.  You might consider examining the effect of
> Waiting_Status_tvc on time to event.
>
> stcox Waiting_Status_tvc
>
> Tom Weichle
> Math Statistician
> VA Information Resource Center (VIReC)
> Edward Hines Jr. VA Hospital, Bldg 18, 202E
> 708-202-8387 ext. 24261
> Thomas.Weichle@va.gov
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/



-- 
Kyleigh Schraeder, BSc (Hons)
M.Sc. Candidate
Clinical Psychology Program
Department of Psychology
University of Western Ontario
kschraed@uwo.ca

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/