t-test
Message posted by steve on October 16, 2000 at 12:00 AM (ET)

I am currently working on a project that requires us to test inter-observer error. It requires us to administer a pain test that has the subjects quantitate the pain numerically. My question is how to best test the difference between the number one observer gets compared with another on the same set of subjects. Any help is greatly appreciated - please be simplistic in your responses (I have a feeling the t-test is the way to go and I can calcuate that on excel - but what does the number mean.) thanks

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: t-test
Message posted by JG on October 17, 2000 at 12:00 AM (ET)