Conversations (2)
Éowyn Banerjee The denominator for the conversion rate includes non-converters, but should it? The definition matters.
I'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.
The Reykjavík boundary discontinuity in 2014 occurred because of a municipal merger, and our figures jump accordingly. However, historical data for the merged municipalities exists in separate files, but it's keyed by the old administrative codes. Should we attempt to align the historical data with the current boundaries, or should we clearly document the break?
Works for me.