The three sets of ground‐motion predictions (GMPs) of Boore (2018; hereafter, B18) are compared with a much larger dataset than was used in deriving the predictions. The B18 GMPs work well for response spectra at periods between ∼0.15∼0.15 and 4.0 s after an adjustment accounting for a path bias at distances beyond 200 km—this was the maximum distance used to derive the stress parameters on which the simulations in B18 are based. An additional offset adjustment is needed in the B18 predictions for short and long periods. The adjustment at short periods may be because the κ0κ0 of 0.006 s stipulated by the Next Generation Attenuation‐East (NGA‐East) project to be used in deriving the GMPs is inconsistent with the observations on rock sites. The explanation for the offset adjustment at long periods is not clear, but it could be a combination of limitations of the point‐source stochastic model for longer period motions, as well as a decreasing number of observations at longer periods available to constrain the simulations on which the predictions are based.

The predictions of B18, developed for very‐hard‐rock sites (⁠VS30VS30 of 2000 and 3000  m/s3000  m/s⁠), have here been extended down to VS30VS30 values as low as 200  m/s200  m/s⁠. I find, as have others, that for a given VS30VS30⁠, there is generally less site amplification for central and eastern North America (CENA) than for the active crustal region dataset used for the Boore, Stewart, et al. (2014; hereafter, BSSA14) GMP equations. This might have an impact on conclusions of several previous studies of CENA GMPs that used the site amplifications in BSSA14 in comparing data and predictions.

An additional finding is that the κ0κ0 implied by recordings on a subset of stations in the Charlevoix region located on rock (data from these stations were not used in the analysis described earlier) is more consistent with a value near 0.014 s than the 0.006 s value used in B18 and the NGA‐East project.