In an experiment, 20 project experts (10 from technical roles and 10 from non-technical roles) were instructed to estimate the effort required to complete a web development project.They could use their prefered estimation strategy. They each provided effort estimations in work-hours.

There is a hypothesis, that technical roles provide more optimistic effort estimates than experts in non-technical roles. How could that hypothesis be statistically proven with the available data?

  • $\begingroup$ You might want to provide more information on the data you have. How was effort measured? How many people were asked? $\endgroup$ Jan 16, 2015 at 8:42
  • $\begingroup$ Please explain what you understand thus far & where you are stuck. Then we will provide hints to help you get unstuck. $\endgroup$ Jan 26, 2015 at 3:28

1 Answer 1


Depending on wheather the variances in your groups (technical / non-technical) can be assumed to be equal you can use Student's t-test or Welch's t test to test if the means of both groups are significantly different.

Equal Variances: Student's t-test / Unequal Variances: Welch's t test

To test if the variances can be assumed to be equal you can use Levene's test. Another test you could use is Bartlett's test.

Because you have a directed hypothesis (mean of technical < mean of non-technical) you have to use the one-tailed test.

Have a look at the wiki pages for the Student's t-test and Welch's t test for more information.

  • $\begingroup$ I also added information on using one-tailed test because your hypothesis has a direction. $\endgroup$ Jan 16, 2015 at 10:50

Your Answer

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

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