Conversations (3)
Reconciling this with the other chart
Should the anomaly be as a share of total for this comparison to mean anything?
a rebasing in the last decade?
Is internet penetration index-linked here?
adjusted definition changeI've been concerned about this for a while — your approach of separating the analysis by cohort maturity sidesteps the aggregation bias that was confounding the earlier dashboard.
Can we batch these updates?
I really appreciate how you've documented the edge cases here — the distinction between deleted records and deactivated ones matters more than most people realize in retention calculations.
Nice — the H2 view helps.
Aino Ngata What's the denominator here?
this contradicts the other chart — one of the two is inverted.