Independence of the data

#1
Hello.
I assigned 18 participants to the experimental group (n=10) and control group (n=8). The experimental group received intervention A and the control group received intervention B. After 6 weeks, I applied intervention A to the control group (n=8). Then, I mixed the data of both groups which received intervention A (18 participants) and compared them with the data of the control group which received intervention B (n=8). The results are very interesting! I received a comment from a researcher that it is a violation of the dependence of data. Would you please assist me to find support for the way that I mixed the data? In fact, I need to support the way that I mixed the data to publish the data.

I appreciate your kind attention to my request.
 

katxt

Well-Known Member
#2
As I interpret your question, you want to compare two sets of data which partly overlap. Ways of doing this have been devised.
You could try googling "partially overlapping samples t-test". eg https://www.tqmp.org/RegularArticles/vol13-2/p120/p120.pdf
Or you could possibly try a repeated measures analysis with missing data?
Or you could try a randomization test that keeps the dependence intact. This is probably what I would do.
 

hlsmith

Less is more. Stay pure. Stay poor.
#4
Question #1, did you randomize treatment allocation?

Correct, not addressing the partial dependence would be misleading. You conducted a crossover study, but forgot to allow the treatment group to receive the control. Is there a reason for this (e.g., they were healed, couldn't sufficiently washout the the treatment effect)?

You never told use how the outcome was formatted and distributed!