# Thread: Calculating Bayes statistic from a t-test result

1. ## Calculating Bayes statistic from a t-test result

Hi,
Part one of the study in question analysed whether participants had a preference for chocolate when eating alone compared to eating with someone else. The results for that study were significant- participants enjoyed the chocolate when accompanied compared to alone. For the second part they wanted to test to see if the same results would occur if the chocolate was substituted for a bitter version. The rating scale was from 0(least liking)-10(highest liking). My task is to calculate a Bayes statistic from this 2-tailed paired t-test. The results from the t-test were t(21)= 2.42, p= .025, d=.34, 95% CI [0.10, 1.31]. The means and SD for the two conditions were for the shared condition (M= 2.45, SD= 1.77) and for the non-shared condition (M= 3.16, SD= 2.32). I am unsure how to work out where the prior probability would come from, as well as how to know whether the distribution is uniform or not and by being a 2-tailed test if that would affect the Bayes statistic.
Any help would be much appreciated,
Thanks!

2. ## Re: Calculating Bayes statistic from a t-test result

There are many ways to do a Bayesian analysis, so this one is hard to answer without having a better idea of the methods you are expected to learn in your course.

Has your instructor covered similar problems? Has the course focused on Bayes Factor tests, or calculating posterior probability distributions? What kind of priors has your instructor uses for cases like these in previous examples?

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts