The regional aggregate includes an "unallocated" category that represents 2-5% of the total, but its composition isn't documented. This black hole makes it hard to assess data quality and impossible to reconcile with component-level totals. Should we either break down the unallocated category or exclude it from the aggregate?
Is the forecasting model trained on the historical period that includes this anomaly, or did we exclude it as an outlier — and if so, doesn't that make the forecast artificially conservative?
Akira Hammerhand Well done. See /u/plg_aragorn_bolger/p/plot-0060.
Confirmed.
I agree.
Colour order does not match the legend order.
Is the baseline pre-promotion or post? See /u/plg_aragorn_bolger/p/plot-0060.
The units are missing from the colour scale.
population here is clipped; it should be as a share of total.
Works for me.
Fixed.
Fair point.
Is GDP in absolute terms across the whole window?
See the other chart.
Clear.
Arwen Ironfoot I was thinking the same.
What happened to MEA around 2015?
Same conclusion here.
Worth noting South Africa and LatAm are not measured the same way over the first half.
Well reasoned.
Leane Vasquez Spot on.
We hit the same thing last Q1. The fix was to hold
Q3 constant.The análisis looks solid. See /u/plg_aragorn_bolger/p/plot-0060.
the tick labels comes across as off.
The timestamp is in a different timezone. See /u/plg_aragorn_bolger/p/plot-0060.
This is much clearer, thanks.
Missing 2006.
Confirmed.
Worth noting — we should discuss methodology going forward.
Worth noting the UK and Japan are not measured the same way over the post-2020 window.
Can you split H2 out?
Not sure what
Year is measuring.Vera Mayene Y-axis should start at zero.
The pattern makes sense.
Is the other chart built from the same extract?
Same conclusion here.
Kavya Rasmussen Should we use a stacked view?