Using the Crawford and Garthwaite (2002) modified t-test for the reverse purpose?

#1
Hi All,

I would like to compare features in people's vocalizations after imitating a target to the target itself. My aim is to measure how much they have deviated from the target. I've thought of using the Crawford and Garthwaite (2002) modified t-test. This is normally used to compare a single patient to a control group (considered as 'normal' baseline). I was wondering whether I could use this test for the reverse purpose: compare the group of participants to a single target (which for our purposes is now considered the normal baseline). Do you think this would make sense? Or do you have any other alternatives in mind? Please let me know whether I need to clarify any of these points.

Reference
Crawford, J. R., & Garthwaite, P. H. (2002). Investigation of the single case in neuropsychology: Confidence limits on the abnormality of test scores and test score
differences. Neuropsychologia, 40, 1196–1208.
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
like to compare features in people's vocalizations after imitating a target to the target itself.
I didn't really understand this sentence. Why couldn't you just do a one-sample t-test?
 
#3
Re the unclear point, I meant that I am comparing jitter (a type of fundamental frequency variation) in the voice of participants. Yes, fair enough. I am just used to running tests with multiple control groups and doing just a one-sample t-test didn't occur to me, but it sounds like the most sensible thing to do given the simple present design. Many thanks for your reply!!