Introduction

Seasonal adjustment is the process of estimating and removing from a time series systematic calendar-related fluctuations that occur at the same time and in a similar magnitude each year. Once those are removed, what remains is the trend and irregular movements of any time series.

Residual seasonality arises when the seasonal adjustment process has failed to remove all seasonal variation.

In recent years, quarterly (and monthly) GDP statistics published by ONS have shown stronger growth in the first half of the year than in the second half. Since 2022, based on first-release data, growth in the first and second quarters has averaged 0.6% and 0.3% respectively, while the third-quarter average has been nearly flat, with an average contraction of 0.1% in the fourth quarter. This has prompted some users, and media commentators to suggest that there may be residual seasonality in recent quarterly GDP statistics.

However, this recent pattern of stronger growth in the first part of the year has reflected, at least in part, a series of one-off events (for example the bringing forward of economic activity in advance of the expected imposition of tariffs by the USA).

In September 2025, ONS discovered and corrected an error in the seasonal adjustment methods applied to retail sales. ONS considers that the impact of the correction on GDP is minor and has been incorporated within revisions to quarterly and monthly GDP in the 2025 Blue Book. ONS has said that the error had its roots in features specific to the reporting calendar adopted in the retail sector and therefore has limited implications for other sectors or for the headline aggregates. ONS was transparent in identifying, and prompt in correcting, the error.

ONS has also published an updated version of its assessment of the effectiveness of its approach to seasonal adjustment, with a focus on the top-level aggregate: monthly and quarterly GDP. This assessment concluded that the approach adopted is consistent with international best practice and that there is no evidence of residual seasonality in the published series for GDP.

The methodologies for seasonal adjustment, and the associated statistical tests of effectiveness, are specialised topics employing complex techniques. Applying them requires a high level of expertise.