For a school science fair project, my daughter randomly divided a population of subjects into a control group and three experimental groups. We recorded the time each subject took to perform a certain task. Now we want to analyze the four sets of time data to decide, for each of the three experimental groups, if subjects in that group took more or less time overall to perform the task than subjects in the control group.

What is an appropriate procedure for comparing the times between two groups, and how do we decide if the difference is significant?

Perhaps there is some method that takes into account the difference in two groups' mean times, and compares the difference with the overall dispersion of the times? But if so, I don't know what it is or what it is called. A pointer to the literature (or to Wikipedia) would be helpful.

I have a strong mathematics background, but I don't have any specific expertise in statistics.

If I omitted anything important in my description, please leave a comment and I will supply it.

  • $\begingroup$ Why isn't your daughter doing the asking? $\endgroup$
    – Russ Lenth
    Oct 29, 2014 at 3:16

1 Answer 1


Read up on one-way analysis of variance (ANOVA) followed by Dunnett's multiple comparison test. That does exactly what you are asking for.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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