Brand awareness metrics

Looking at the correction factor applied retroactively to 2018, it ranges from 1.02 to 1.18 depending on the region, but the documentation doesn't explain what variation justifies such different correction magnitudes. If the same event should apply equally to all regions, the variation suggests either regional data quality differences or a methodological choice that needs explaining. Should we investigate? See /u/plg_elendil_raza/p/plot-0006.