Thread: Appropriate t-test

When determining the effect of age of a person on the incidence of type II diabetes, is it correct to use an independent t-test?

Thanks

I am not a statistician, but I don't think a t-test is the most appropriate test to use for such a question. A t-test asks whether or not the mean of a group is different from zero or if the mean of two groups are different. So you could use it to ask if there is a difference in incidence between those under 50 and those over 50 (for example) but other methods (like regression analysis) could give you a more complete answer by not binning the ages like that. [http://docs.statwing.com/examples-an...tions/t-test/]

so t-test is more appropriate, for example, when comparing bmi of males and females or when determining the difference between treatment and control group??

As far as I understand things, yes.