Fig. 2
From: Reply to: fMRI replicability depends upon sufficient individual-level data
Scatterplots showing replicability (unthresholded, Fisher-transformed) as a function of the square root of the number of trials (T), the square root of the number of participants (N), the mean within-participant similarity across runs (ws), and the mean between-participant similarity marginalized w.r.t. within-participant similarity (bs⊥ws). Gray + show the raw values of all variables, while black ○ show the residuals (centered on the original mean) of each variable w.r.t. the remaining three variables
