Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: time averaged exposure in -stcox-


From   Gloria Chi <stata.glochi@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: time averaged exposure in -stcox-
Date   Thu, 18 Oct 2012 21:54:39 -0700

Hello Statalist members,

I have a data set that is in long format and there are multiple
records per participant. For each of these records, there is a
different exposure concentration and the corresponding start time and
stop time (since enrollment) that the participant was exposed. My data
looks like this:

ID no.    Exposure     Start time      Stop time     Time to
failure/censor     Failure
1           12               1                  1200            1200
                          0
1           15               1201             1500            1500
                        0
1           10               1501             2000            2000
                        0
2           20               1                   500             500
                            1
3           33               1                   700             700
                            0
3           40               701               750              750
                          0
3           12               751               1000            1000
                         1
4           16               1                   300              300
                            0
4           20               301               900               900
                           1

I am trying to run a Cox regression but am having trouble with the
exposure. I want to use an average exposure concentration that is time
weighted to the duration of the exposure (as given by the start and
stop times). So at a given failure time, the exposure is the
time-weighted average concentration up until that given failure time.

Secondly, I also want to run a Cox regression with average exposures
over the previous 2 years before a failure and disregard the exposures
that occurred before the previous 2 years.

I have not been able to figure out how to do this in Stata and would
greatly appreciate any advice.

Thank you so much!

Sincerely,
Gloria Chi
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index