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

st: repeated sampling of emergency department patients

From   [email protected]
To   <[email protected]>
Subject   st: repeated sampling of emergency department patients
Date   Fri, 8 Jul 2005 14:36:29 -0500


We have the following dataset: 

Monthly survey of patients who report to an emergency department (across 
15 months) and if they use medication Y  (y/n).  We also have other data 
on the patients' characteristics (X1, X2, etc). 

6 different hospital emergency departments were surveyed.  Each month we 
targeted 15 patients, but sometimes less (or more) were enrolled. 

ID          Emer Dept   Date    Smoker          Age     Medication Y
1               1       jan03   Y               10      Yes
2               1       jan03   N               45      No
3               2       feb03   Y               23      No 

And so on 

We are trying to assess whether: 

1) Use of Y changes across time
2) If X1, X2 are predictors of use of Y
3) Use of Y is associated with a particular emergency department 
4) A quality initiative started at month 7 makes a difference in the use 
of Y 

I initially thought that GEE would be an appropriate way to analyze this, 
but we don't repeatedly measure one individual over 15 months.  Instead, 
we are sampling 6 emergency departments monthly  over 15 months.   Then I 
thought STATA's time series would be appropriate.  This doesn't appear to 
be appropriate, as again, STATA's time series functions seem to operate 
with one individual as the unit being measured repeatedly.  Finally, I 
thought STATA's survey functions would be helpful, but those don't seem to 
be setup for repeated measurements. 

I've extensively checked STATA's reference manuals, Fitzmaurice's Applied 
Longitudinal Analysis, Twisk's Applied Longitudinal Data Analysis for 
Epidemology, and Levy's Sampling of Populations.  I understand the data 
structures for the examples cited in their discussions, and did not find a 
parallel to the above. 

Now I'm in a quandry.  The best I could currently think of is to consider 
each ED as a "unit" and consider that it is measured repeatedly across 
time.  But then I can't seem to understand how to use STATA's GEE as each 
"unit" has mutiple measurements at one time!

Thank you in advance, 

Richard Lenhardt
Assistant Professor of Medicine
Rush University Medical Center
Chicago, IL 

*   For searches and help try:

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