Without going into domain specific information, I have a data set in which I'm testing the rate of occurrences of an event like so:

Event 1

# of trials: 378

# of occurrences: 109

# of occurrences in case 1: 12

# of occurrences in case 2: 45

# of occurrences in case 3: 51

I want to find out if there is a significant difference in the occurrence of the event between those three test cases. I expect that case 1 will be significantly different, while case 2 and 3 will show no significant difference in their occurrence.

I think I need a chi square, but I can't for the life of me figure out how to set it up because I only have one dimension.

Thank you in advance.


You'll want to use a hypothesis test for proportions. To the extent of my knowledge, you'll want to test the difference between the proportions of each variable (i.e - H0: C1 = C2, H0: C1 = C3, H0: C2 = C3) but there may be some kind of method to test all three at once that someone else can suggest.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.