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 on April 23, and its replacement, is already up and running.

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

st: RE: adjusting variables in metanalysis

From   "Trelle Sven" <>
To   <>
Subject   st: RE: adjusting variables in metanalysis
Date   Wed, 20 Feb 2013 11:44:02 +0100

Vasan Kandaswamy asked:
"Dear all,
I have more of a  statistical question and any help would be very useful. In the meta-analysis that I am currently working on, I am investigating the effect of a genetic variant with diabetes risk. We have used abstracted data from published studies and do not have access to raw data sets. Therefore, I have the OR (95%CI) for disease risk for 10 studies. Now I would like to adjust the already calculated OR for a variable such as BMI ( individual mean BMI is available for all studies). Is there a possibility to do this. I hope I have made my question clear. Suggestions would be of great help.

[ST] I am not sure what you mean by "adjusting" in this context but you can investigate the effect of BMI on the effect estimate i.e. the odds ratio (interaction) by using meta-regression (ssc install metareg). Note however, if you have only study level data (in your case mean BMI) this is prone to ecological fallacy/bias (e.g. Berlin JA, Santanna J, Schmid CH, Szczech LA, Feldman HI. Individual patient- versus group-level data meta-regressions for the investigation of treatment effect modifiers: ecological bias rears its ugly head. Stat Med 2002; 21: 371-87.).
[ST] Best
[ST] Sven Trelle

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index