Conversations (2)
Imani Brockhouse 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?
Fully aligned.
Definitely.
Very good.
I had this wrong earlier. Norway is fine; it was
Q3 that was clipped.raw_metric should probably be per capita.Same conclusion here. (edited to fix a unit)
Très bien — this level of detail on the assumptions is exactly what we need when presenting to stakeholders who might challenge the methodology downstream.
Should use thousands separator.
The restatement to correct for double-counting in 2020 reduced the aggregate by 8%, but the reduction wasn't evenly distributed—some subcategories dropped 15% while others barely changed. This asymmetry suggests either some categories were double-counted more than others, or the restatement logic was applied inconsistently. Should we audit the correction by category?
Wait, which of these is MEA?
Fair enough.
Thanks Kavya Lindqvist, that resolves it.
Worth cross-referencing with the ops log. See /u/plg_sheriam_beridze/p/plot-0159.
Matches our numbers too.
Wait, which of these is India?
Does this include refunds?
Why such variance in Q2? See /u/plg_sheriam_beridze/p/plot-0159.
Moving this to the H2 agenda.
Decimals are inconsistent between Norway and Vietnam.
Can you share the extract?
Should we use a stacked view?
The "Null" category is distracting.
Fair enough.
Same conclusion here.