Table 2 Statistical power analysis.

From: Improved data quality and statistical power of trial-level event-related potentials with Bayesian random-shift Gaussian processes

 

\(n = 15\)

\(n = 25\)

Empirical H-L

0.65

0.9

RPAGP H-L

0.85

1.0

Empirical H-N

0.95

1

RPAGP H-N

1

1

Empirical L-N

0.50

0.50

RPAGP L-N

0.75

0.90

  1. Estimated power in testing for differences in mean amplitudes across conditions for empirical bootstrap and RPAGP on ERP data. RPAGP consistently shows power at least as great as the empirical testing power, with the greatest increase in testing the difference of Low and Neutral conditions.
Back to article page