Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: survival analysis vs ols

From   =?UTF-8?B?Um9uw6FuIENvbnJveQ==?= <[email protected]>
To   [email protected]
Subject   Re: st: survival analysis vs ols
Date   Wed, 06 Oct 2004 16:28:10 +0100

Zhu, Carolyn wrote:


We are trying to estimate the effect of ER room conditions on the time it takes for patients to receive treatment A. All patients received treatment A some time their ER admission so we don't have any right censoring problem. I was just told that in this case survival analysis and OLS give the same results. Is that correct?



Survival analysis has one great advantage here: you can the shape of the distribution of time to treatment as a nuisance parameter, something to be got out of the way before getting down to the real work. You can report quantiles of interest, and use the graphs available to very good effect.

Analysing times using OLS can be problematic. The distribution looks funny, and some people (not in your case) never make it. One solution that often gives quite an acceptable data distribution is to use the reciprocal of time, which has a common-sense interpretation: speed. People who never make it have a speed of zero.


Ronan M Conroy ([email protected]) Senior Lecturer in Biostatistics Royal College of Surgeons Dublin 2, Ireland +353 1 402 2431 (fax 2764) -------------------- Just say no to drug reps

* For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index