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: Left truncation in survival analysis

From   Steven Samuels <>
To   Yigit Aydede <>,
Subject   Re: st: Left truncation in survival analysis
Date   Thu, 28 Apr 2011 09:11:33 -0400

You are welcome, Yigit.  

In Statalist, a  private thank you note is always appreciated, not only by the recipient but by others for whom it's not informative.  I am forwarding your post to the list because there is still a substantial issue.

But no, the name of your phenomenon *is* left truncation. Left censoring occurs when you know for some individuals only that the event took place prior to a certain time.  An early article that addressed this phenomenon was: Wagner, S.S., and S.A. Altmann. 1973. What time do the baboons come down from the trees? (an estimation problem). Biometrics 29 (4): 623-635.   On some mornings, the observer arrived too late to see what time the baboons descended.


On Apr 28, 2011, at 8:42 AM, Yigit Aydede wrote:

Hi Steve,

Thanks a lot for your response.  And thanks for the reference.  I guess the name of my problem is left-censoring. I checked it in the literature and I saw different definitions for it.  There are some suggested solutions to it, but I am not sure if they are robust enough.  Some say left-censoring can be treated as interval censoring (An Introduction to Survival Analysis Using Stata - Cleves et al).  I guess I need to read more.  

Sorry for writing this directly to you but I don't know how to response your e-mail by using Statalist.


Yigit Aydede
Department of Economics
Sobey School of Business
Saint Mary's University
Halifax, Nova Scotia, B3H 3C3
T (902) 420.5673
F (902) 420.5129

*   For searches and help try:

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