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]

Re: st: Need to Determine an Intervention Effect using xtmixed

From   Ronan Conroy <>
To   "" <>
Subject   Re: st: Need to Determine an Intervention Effect using xtmixed
Date   Wed, 5 Sep 2012 11:12:34 +0100

On 2012 MFómh 4, at 22:58, Elizabeth Prezio wrote:

> I need some sort of "intervention effect" comparing the adjusted HbA1c
> (test) values over  12 months between the intervention and control groups. I
> need 95% CI and a P-value.

It is up to the person or people who asked you for an intervention effect to say exactly what they mean. There are a number of ways of thinking about intervention effects.

As you can see, there is no single statistic that defines the effect of an intervention. To begin with, you might ask what the effect of the intervention would be on the population as a whole, or on the individual who receives it. Secondly, you need to define whether you will measure the effect of the intervention assuming that any other differences between treated and control groups are irrelevant, or whether you measure the effect in a contrafactual scenario in which there are no other differences between the groups.

And so on.

Talk to your supervisor for clarification. 

Part of the problem may be that you need to be clear as to what each of the measures you calculated tells us about the efficacy of the intervention. But don't calculate until you get a clear answer from these people.

> Any help would be greatly appreciated.

Ronán Conroy
Associate Professor
Division of Population Health Sciences
Royal College of Surgeons in Ireland
Beaux Lane House
Dublin 2

*   For searches and help try:

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