Skip to main content
. Author manuscript; available in PMC: 2021 May 15.
Published in final edited form as: Neuroimage. 2020 Feb 20;212:116630. doi: 10.1016/j.neuroimage.2020.116630

Figure 4:

Figure 4:

The true (solid line) and estimated (dashed line) pERPs are matched based on the regression coefficients from regressing the true pERPs on the estimated pERPs in the low noise (top row) and high noise (bottom row) simulations. Recall that pERPs can be estimated only up to rotations (linear combinations) of those that generated the data. Accordingly, in some cases the true and estimated pair look almost identical, but in others the estimated pERPs appear as combinations of true pERPs.