Is urban share as a share of total across the whole window?
Yuki Noakes The methodological note explains the gap.
What's the minimum sample size?
Malik Prescott The color convention isn't obvious.
The 1997 tick is inverted.
I think the 2020 data might be affected by the methodology change. Should we note that?
Pedro Proudfoot Could the variance in Q2 be explained by a shift in the user composition rather than a genuine change in underlying behavior — are we segmenting by cohort maturity or acquisition channel?
Absolutely.
Stale.
I do not follow — is the anomaly going up or down here?
Colour order does not match the legend order.
Should we consider the adjusted baseline instead?
Source?
Correcting myself: the anomaly is in absolute terms, so the comparison holds.
Nice — the H2 view helps.