Pick up to 4 countries and a period. The selection is kept in the address, so the view you are looking at is the view you can send someone.
Germany's economic output was 1.0% in Q2 2026.
1.2%
is expected by Q2 2027 — higher than today. It could plausibly be as low as -1.8% or as high as 4.3%.
That range is not a guess about how sure anyone feels. It is how far this method has actually been off in the past, so four times out of five the answer has landed inside it.
% YoY. Sources: Germany, Euro area — Eurostat. Retrieved 2026-08-29. Everything after the dotted line is a forecast, not a record. The shaded band is the range this method has landed in four times out of five in the past. No language model produces any of these numbers.
Take it with you:
The methods do not agree
The chart above draws one forecast, because five dashed lines in one frame is a thicket. Here is what each method expects on its own — run on the same numbers, and still landing in different places. That spread is not a flaw to be hidden; it is the size of what nobody knows yet.
Germany, Q2 2027. The dot is what each method expects, the bar how far it would not be surprised to be wrong. They are run on the same numbers and still land 1.2% apart, which is the honest size of the disagreement — and the reason the chart above draws the middle of them rather than picking a favourite.
What is already settled
A year-on-year rate compares this month with the same month a year earlier, so part of the coming year's rate is decided the moment an old month leaves the window — before any price moves. The bars split the forecast into that part and the part that still needs new price movement.
Germany, Statistical baseline. For Q3 2026 the base effect alone accounts for +1.05 of the expected +1.34; the rest is momentum. The two always sum to the expected rate, because the split is arithmetic rather than a second model.
Has it been any good?
Every method above was replayed from each of the last three years' starting points, seeing only what was known at that point, and scored against what actually happened. A forecast without this is a decoration.
How far each forecasting method has been off in the past, and how often its stated range held.
Method
Usually off bya quarter ahead
Usually off bya year ahead
Its range heldit claims 80 in 100
vs. the simple rulebelow 1.00 is better
Assume last year repeats
1.86 pp
1.74 pp
9 in 10
1.00
Theta
0.97 pp
1.74 pp
10 in 10
1.01
The middle of all methodsthe one drawn above
1.00 pp
2.06 pp
10 in 10
1.20
Exponential smoothing
0.98 pp
2.07 pp
10 in 10
1.20
Automatic ARIMA
1.11 pp
2.34 pp
10 in 10
1.34
Germany, measured over the last 33 starting points. The last column compares each method against the simplest rule there is — assume this period repeats what it did a year ago. Below 1.00 means smaller errors than that rule, above it means worse. All of it is measured against today's revised figures rather than against what was known at the time, which flatters every method here a little.
How this is measured
The stored quantity is the price index; the rate shown here is derived from it against the same month a year earlier. That direction matters: deriving the rate keeps base effects intact, where modelling the rate directly would treat them as noise.
Countries come from different providers with different publication lags, so the series do not all end in the same month. Each one is charted to its own last observation rather than trimmed to the shortest, and the source line names the provider.