Comparing Median and Median Absolute Deviation (MAD)

#1
Hi,

I have 3 focus groups each consisting of 4 people. They all rated a list of quality indicators (ratings were between 1 to 9, 1 being less important and 9 being most important). I want to see if there is any difference in the ratings based on their education level.
Since the power is so small for each of the group (only 4 people), I don't know how to compare the ratings? Should I be comparing the mean or median or MAD? And what test should I be using to compare these?

Any ideas or suggestions will be greatly appreciated!

Thanks
 

JohnM

TS Contributor
#2
To be completely honest, I wouldn't recommend doing any statistical testing on focus group data - the samples are too small, and they are definitely not representative samples of the population.

If you want to look at basic observations for interesting patterns, and then formulate hypotheses that will later be evaluated with more rigorous methods, then that's fine.