Different Bayes Factors from different JASP modules?

JonR

Hi all,

I am new here and new to Bayesian statistics - however, loving JASP!

Here is my problem:

I am looking at a student's dataset and have run the Bayesian Paired T-test (from the JASP default menu and settings), and I get a BF10 of 6402.23 (frequentist output, if of help: t = -11.72, sample size = 8).

However, in the Summary Statistics module, inputting the results from the frequentist outputs (t = -11.72, sample size = 8 [the same default prior]), the BF10 is 2413.02.

And again, if I run this in R (I am new to R but have input the same frequentist outputs (t = -11.72, sample size = 8 [the same default prior]), the BF10 is 7.78.

Can anyone help?

(I know there are limitations with small sample sizes - here, n=8; however, it's more for teaching purposes. Perhaps this is the issue?)

Many thanks,

Jon

EJ

Hi Jon,

This is puzzling! I confirmed the output from the Summary Stats module. The result from R seems wrong, because the result is so overwhelming -- are you sure you ran a paired t-test? Could you perhaps share the data and the R code? Also, I need to data to conduct the same analysis using the regular Bayesian t-test.

Cheers,

E.J.

EJ

Update: I have created some random data to yield the specific t-value, and when I run the two tests in JASP I get the same result. So it is somewhat mysterious why you find a difference. Maybe we can figure it out if you have the data.

EJ

JonR

Thanks EJ.

I have rechecked my data... and, I am now getting the same results. It looks like this wasn't copied over correctly. Sorry about the trouble here, and thank you for looking at it.

EJ

Thanks for the update, and good to hear!

EJ