SERforum

 

Join Andrew Olshan, for SERforum Live!

“Career and Professional Development”

JOIN SERforum – Live
December 5th, 12pm EST

 

Do you ever find yourself struggling to figure out a question about epidemiologic methods, or other topics in epidemiology, and don’t know who to ask? The SERforum allows for individuals to answer questions that come up in our daily work around substantive and methodological topics in epidemiology.
 
All topics may be viewed, but to read and post comments, SER membership is required. If you are member, login! Not a member, join us!

Forum Navigation
You need to log in to create posts and topics.

Quasi-experimental cluster design

Hello,

I'm collaborating on a grant that has a slightly unusual design, which I'm sure has been utilized before but exactly what to call it (and therefore how to start researching its application) is escaping me.

It will be a quasi-experimental study where the intervention is administered at the clinic level, and outcomes ascertained at regular intervals at both the clinic and individual (in this case, healthcare worker) level. The intervention will be implemented in four stages corresponding to four modules, and outcome will be measured at baseline and at least 12 times after each stage of intervention is implemented. There are no control clinics.

I'm thinking the best way to describe this is a quasi-experimental study with pre- and post-test samples, but that is quite long, and doesn't address the fact that it's also multi-level. Any thoughts?

Many thanks,

Julianne

Sorry,  I’m not clear on the design.

Is each clinic receiving 4 modules? And the intervention the full four modules where follow up begins at the end of 4 modules? Or you want to evaluate parts of the intervention as if it is a multiple component intervention? Or is it that the clinics are receiving the intervention in a staggered manner for logistical reasons, and there are four staggered groups? If the latter, it seems like a step-wedge design.
I’m not a statistician but I don’t see why the multi-level design would be treated differently here than other studies.
Ian Shrier