Fluorite | Level 6

Compare rate reduction between groups

I have some pre-post data on 2 groups. The data is binary (Y/N) and I am specifically interested in comparing the rate reduction between the 2 groups (the number of Yes's that turned to No after the intervention). What statistical test should I use to determine whether there is a statistically significant difference between the 2 independent groups?

4 REPLIES 4
SAS Super FREQ

Re: Compare rate reduction between groups

Usage Note 37344: Estimating rate differences (with confidence interval) using a Poisson model
https://support.sas.com/kb/37/344.html

Koen

Fluorite | Level 6

Re: Compare rate reduction between groups

So are you proposing to generate a new outcome variable (change = 1 if Yes at pre and no at Post), 0 otherwise) and use that as the outcome?
SAS Super FREQ

Re: Compare rate reduction between groups

Hmmm.
Might not be ideal as you have 4 situations (PRE versus POST) :
* YES YES
* NO  NO
* YES NO
* NO  YES

I like the analysis proposed by @Ksharp !

It's often worthwhile to screen the SAS Communities for similar topics.
This one comes close I think :
Home > Health > Health and Life Science > Comparing rate ratios
Comparing rate ratios
Posted 03-24-2016 09:46 AM (1895 views)
https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/Comparing-rate-ratios/m-p/258797#M2044

And although you can probably NOT use the below analyses right away, I think they will be of interest to you :

Usage Note 22561: Testing the equality of two or more proportions from independent samples
https://support.sas.com/kb/22/561.html

Test for the equality of two proportions in SAS
By Rick Wicklin on The DO Loop July 5, 2017
https://blogs.sas.com/content/iml/2017/07/05/test-equality-two-proportions-sas.html

Cheers,
Koen

Super User

Re: Compare rate reduction between groups

Since your data is pairs data with binary response,
you could use GEE or Mixed model for Estimating the risk (proportion) difference.
(a.k.a take it as repeated measure method)
Check this out:

https://support.sas.com/kb/46/997.html
Discussion stats
• 4 replies
• 707 views
• 3 likes
• 3 in conversation