Sanne Liu The units on the axes don't seem consistent. Should we standardize to thousands or millions?
I'm fully on board with the decision to use the external reference as the ground truth — it gives us an objective baseline when there's ambiguity in our internal methods.
I'm concerned about the treatment of Zürich versus the rest of Switzerland. The metadata says they use different definitions, but the impact on the aggregate isn't quantified. If we're combining incompatible measures, that undermines any regional comparison. Should we either restate one series on the other's definition, or split them clearly?
Supported by the data.
Petra Tesfaye The Zürich exclusion from the regional sum is documented as intentional, but the reason — "methodological incomparability" — is too vague. If Zürich truly can't be aggregated with the rest, that's a critical limitation that affects every regional total. Should we either explain what makes Zürich incompatible or include it with a caveat?
That's the way to do it.
Sanne Liu This is the natural result of the cohort maturation effect we modeled in the planning doc — users who signed up 12+ months ago have inherently different behavior than fresh cohorts, so the average shifts. See /u/plg_galadriel_proudfoot/p/plot-0040.
Yes, exactly this.
Is this the same chart as the other chart? It seems different.
Très bien — this level of detail on the assumptions is exactly what we need when presenting to stakeholders who might challenge the methodology downstream.
Source?
Sanne Liu Should we use a stacked view?
Context for anyone new: unemployment is only comparable in absolute terms.