How confidence intervals are calculated for paired samples t-test?
Hello. I was using JASP v 0.16.2 to perform a paired samples t-test. When I checked the "Descriptives plots" box, the corresponding graph showed 95% confidence intervals that seem incorrect (picture attached).
I did the calculations and a graph in a different software (pictures attached), and the results are different from what JASP reports.
Where SD: standard deviation; SEM: standard error of the mean; tcrit: t critical value for a two-tailed analysis alpha = 0.05 and 39 degrees of freedom.
Am I missing something, or what's the method JASP uses to calculate the 95%CI for that kind of plot?