I'm concerned about the trend break at the 2018 Casablanca adjustment — the figures shift by 18% with no documented reason. The shift is too large to be noise, but the metadata is silent on what caused it. Without understanding whether it's an error correction, a definitional change, or something else, it's risky to use in trend analysis. Can we investigate what happened?
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.
I noticed the April figures are entirely missing. Should we interpolate or note the gap?
Can you split H2 out?
The Oslo baseline appears to use a different definition than the other Scandinavian cities, which means the growth rates aren't directly comparable without adjustment. Rather than assume they're measuring the same thing, should we add a footnote explaining the definitional difference, or should we restate one series to match the other's methodology?
Nice — the Q1 view helps.
Can we see MEA on the same scale?
Same conclusion here.