Table 4.
Bayesian analysis for the comparison of symbolic analysis parameters among caffeine supplementation conditions.
| Experimental condition | Prior odds | Posterior odds | BF10, U | Probability % | |
|---|---|---|---|---|---|
| V0 | |||||
| PP | PC | 0.587 | 5.36 | 9.13M | 90.1 |
| PP | CC | 0.587 | 12.20 | 20.77S | 95.4 |
| PC | CC | 0.587 | 0.11 | 0.18a | 15.2 |
| V1 | |||||
| PP | PC | 0.587 | 0.25 | 0.42a | 29.5 |
| PP | CC | 0.587 | 0.12 | 0.20m | 16.7 |
| PC | CC | 0.587 | 0.26 | 0.44a | 30.4 |
| V2 | |||||
| PP | PC | 0.587 | 2.23 | 3.76M | 79.0 |
| PP | CC | 0.587 | 23.00 | 39.16VS | 97.5 |
| PC | CC | 0.587 | 0.19 | 0.32m | 24.4 |
The posterior odds have been corrected for multiple testing by fixing to 0.5 the prior probability that the null hypothesis holds across all comparisons (Westfall, Johnson, & Utts, 1997). Individual comparisons are based on the default t test with a Cauchy (0, r = 1/sqrt(2)) prior. The “U” in the Bayes factor denotes that it is uncorrected (PP: Placebo–Placebo; PC: Placebo–Caffeine; CC: Caffeine–Caffeine). Letters indicate the outcome classified as: A = anecdotal; M = moderate; V = very strong; E = extreme favoring the alternative hypothesis; a = anecdotal; m = moderate favoring the null hypothesis.