There are differences between the business investment chained volume measure seasonally adjusted estimates in this dataset and the official estimates published in the Business investment release. These differences are because of the different seasonal adjustment approaches. In this dataset, industry-level series are seasonally adjusted and aggregated. In the Business investment release, the asset-level series are seasonally adjusted and aggregated. This can give different results for the aggregated series. The estimates in the Business investment release should be considered the official statistics.

Please note that not all series will sum to totals because of rounding. These differences are well within the uncertainty of the estimates.

Based on specific user feedback and engagement, we are reviewing our published data for the historic time series for gross fixed capital formation (GFCF) for the years preceding 1997. Until these investigations have been completed, the historical data series for GFCF should be treated as being under review. Current data for GFCF from 1997 onwards are not affected. Our investigations are expected to be completed by 1 June 2025. We would welcome any further comments and user views. Because of the compilation approach for historical data, any change to a component will be closely assessed to see if this results in revisions to aggregate estimates, including gross domestic product (GDP).

The pre-1997 GFCF dataset, when initially created in 2014, was created by linking the historic estimates to the 1997-onwards series. This is because the short overlap period produced more plausible results than a linking factor derived from a longer time period. However, this introduced uncertainty, as it is not possible to test how well the linking factor accounts for methods changes. This is because no information on the real impact was available, which means that the historic GFCF estimates are inherently more uncertain than the 1997-onwards estimates.