Table 3 Frequentist and Bayesian t-tests on 24-hour choice phase.

From: Levodopa does not affect expression of reinforcement learning in older adults

Measure

t

p

d

95% Conf Int

BF01

Posterior

95% Cred Int

Accuracy

0.906

0.372

0.163

−4.135, 10.730

3.581

0.148

−0.186, 0.482

Choose-A

−0.332

0.742

−0.060

−16.919, 12.188

4.960

−0.052

−0.391, 0.281

Choose-B

0.718

0.478

0.129

−8.725, 18.187

4.115

0.115

−0.214, 0.455

Choose-C

0.878

0.387

0.158

−6.981, 17.519

3.663

0.143

−0.200, 0.494

Choose-D

0.108

0.915

0.019

−13.463, 14.968

5.192

0.019

−0.308, 0.355

Choose-E

0.454

0.653

0.082

−11.277, 17.729

4.744

0.071

−0.252, 0.415

Choose-F

−1.771

0.087

−0.318

−25.002, 1.177

1.301

−0.288

−0.642, 0.055

  1. Statistics from frequentist and Bayesian t-tests on the accuracy and percentage of choices for each symbol at the 24-hour choice test. BF01 > 3 reflects moderate evidence in favour of the null hypothesis. Cohen’s d and 95% confidence intervals are presented for frequentist t-tests, and the posterior median and 95% credible intervals for the Bayesian t-tests. All error % from the Bayesian analyses were < 4 × 10−4.
Back to article page