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

st: survival curves for grouped data

From   Dan Exeter <[email protected]>
To   [email protected]
Subject   st: survival curves for grouped data
Date   Tue, 05 Jul 2005 11:47:22 +0100

Dear all,

I am relatively new to Stata and survival analysis.

I'd like to create a life table and an associated survival curve using data from a 3 year period. Unfortunately, I do not have any date of birth/ date of death/ lost to follow up data, and want to produce a 'current' or 'period' life table rather than a cohort life table

I've been trying the ltable command, but the median survival age is considerably younger than I would expect (having done the analysis in Excel already).

I have a count of the population alive, and population that died, at a given age (0-64years) for a three year period, and separately for males and females.

For example, my data are configured as follows:
age | living | dead | sex
0 | 1000 | 10 | 1
1 | 2000 | 2 | 1

I have these data for 3, 3-year periods, and would appreciate advice on how best to compare the results. Most of the literature that I have come across suggest the Kaplan-Meier and Logrank test. My data do not conform to the Kaplan-Meier requirements, and I am unsure if the logrank is suitable for grouped data.

I would be grateful for any help or suggestions

Best wishes

Dan Exeter. BA, MA(Hons), PhD.
Research Fellow
School of Geography and Geosciences
University of St Andrews
Irvine Building, North St
St Andrews
KY16 9AL
Phone: 01334 463951
Fax: 01334 463949
email: [email protected] <mailto:[email protected]>

* For searches and help try:

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