How much official statistics revise their own past, and what it does to conclusions

Every series the site tracks has changed its own history at least once. Excess-mortality estimates for 2020 and 2021 moved by a quarter or more when the ONS changed method in 2024; census results in 2021 and 2022 rebased population estimates and every rate calculated from them, in some countries by several per cent; late registrations lift recent death counts for months; projection assumptions are rewritten each round, migration most of all; fertility outturns have undershot successive projections in almost every high-income country. None of this is error in the ordinary sense — it is how statistics improve — but its size is rarely reported alongside the figure, and conclusions drawn from a vintage do not always survive the next one. The site's revisions stream records each change as it happens; the driver's question is the pattern behind them: which series revise most, in which direction, and whether the revisions are getting larger as methods become more model-based and less counted. The evidence is accumulating faster than anyone is synthesising it.

Status

building

Direction

strengthening

Would change our view

A systematic comparison of vintages against outturns across countries and series; or an office publishing its revision history as a matter of routine.

Trackers

Gaps

Revision histories for most national series, which are rarely archived; the Japanese and Korean offices' practice; anything on whether users of the figures change their conclusions when the figures change.