Index of Services, UK: September 2026

• Services output for Quarter 3 (July to Sept) 2026 was estimated to have increased by 0.9% compared with Quarter 2 (Apr to June) 2026; this follows quarterly growth in both Quarter 2 and Quarter 1 (Jan to Mar) 2026 of 0.6% and 0.7%, respectively.

• There was a rise in 11 of the 14 sectors in Quarter 3 2026, with the main positive contributing sectors being “administrative, support and service activities’’ (up by 4.1%), “information and communication” (up by 2.1%) and “professional, scientific and technical activities’’ (up by 1.6%).

• There was a fall in 3 of the 14 sectors in Quarter 3 2026, with the main contributing sectors being “education” and “accommodation and food”, with both decreasing by 0.5%.

• Monthly services output was estimated to have increased by 0.2% in September 2026; this follows a fall in August 2026 (down by 0.1%) and a rise in July 2026 (up by 0.5%).

• There were monthly increases in 9 of the 14 sectors in September 2026, with the largest positive contributions on the month coming from “real estate activities” (up by 0.4%) and ‘’transportation and storage’’ (up by 1.4%).

• There were monthly decreases in 3 of the 14 sectors in September 2026 (two sectors saw no growth, or 0.0%), with the largest negative contributions coming from “professional, scientific and technical activities’’ (down by 0.7%) and “information and communication” (down by 0.6%).

Response rates for September 2026

The response rates for September 2026 were 71.0%, based on forms returned. This accounted for 87.0% of total turnover coverage of the sample population. More information is available in our Current and historical Monthly Business Survey (MBS) (services) response rates dataset. 

Data sources and collection 

The Index of Services (IoS) is compiled using data from several different sources (share of overall economy based on latest gross value added (GVA) weights).

These include the: 

• Office for National Statistics (ONS) MBS (36.0%)   

• ONS Retail Sales Inquiry (4.4%)   

• ONS Government Expenditure (15.9%)   

• ONS Households' Expenditure (12.2%)   

• ONS Finance Expenditure (7.3%)   

• ONS Households and non-profit institutions serving households (1.7%)

• Other (1.6%) 

The MBS data are published alongside this release in our MBS turnover of services industries dataset. 

More information on what is included within "other" is available in our Gross domestic product (GDP(o)) data sources catalogue.

The percentage of each data source is based on their gross value added weight.

Our IoS methodology provides more information on the data that underpin these statistics; of particular note is our GDP(o) data sources catalogue.

Value Added Tax (VAT) data are also included for small and medium-sized businesses to help inform estimates. More information is available in our VAT turnover data in National Accounts: background and methodology. 

Quality and methodology 

The data reported in IoS bulletins and datasets are estimates that are subject to uncertainty, for example, sampling variability and non-sampling error. More information on these is available in Section 2 of our Uncertainty and how we measure it for our surveys methodology.

More quality and methodology information (QMI) on strengths, limitations, appropriate uses, and how the data were created is available in our Index of Services quality and methodology information (QMI). 

Accredited official statistics 

These accredited official statistics were independently reviewed by the Office for Statistics Regulation in May 2014. They comply with the standards of trustworthiness, quality and value in the Code of Practice for Statistics and should be labelled "accredited official statistics". 

Revisions to Index of Services

This release gives data for September 2026 for the first time. This release also includes revisions to July 2026 and August 2026. More details are available in our National Accounts Revisions Policy: updated January 2026. 

Table 1 shows the revisions to Index of Services and its main sectors for July 2026 to August 2026 since our last release on 15 October 2026.

Seasonal adjustment

The monthly estimates of IoS are seasonally adjusted. Seasonal adjustment is the process of removing the variations associated with the time of year, or the arrangement of the calendar, from a data time series. 

IoS estimates, as for many data time series, are difficult to analyse using raw data because seasonal effects dominate short-term movements. Identifying and removing the seasonal component leaves the trend and irregular components. 

We use the X-13-ARIMA-SEATS approach to seasonal adjustment. Seasonal adjustment parameters are monitored closely and regularly reviewed. More information is available in our seasonal adjustment methodology. 

In our IoS estimates, seasonal adjustment is applied at the industry level, and the seasonally adjusted series are aggregated to create estimates by sector and total IoS output. As part of our quality assurance approach, residual seasonality checks are regularly completed by our time series analysis team on both the directly seasonally adjusted series and also the indirectly derived aggregate time series. 

Based on our quality assurance as part of this publication, there is no statistically significant residual seasonality in our aggregate estimates for IoS in the period from January 1997 to September 2026.

This topic is explored further in our methodology on assessing residual seasonality, published on 12 May 2026. 

Since June 2026, we have published non-seasonally adjusted chained volume measure series in our updated Monthly GDP low level industry dataset. There are conceptual differences between indirect and direct seasonal adjustment. Indirect seasonal adjustment is the sum of the directly seasonally adjusted component series, typically chosen at an optimal level and depending on user needs.

For the National Accounts, GDP aggregates are created with indirect seasonal adjustment. Because of processing, which includes benchmarking and chain-linking, direct seasonal adjustment of the non-seasonally adjusted GDP aggregate will not give the same results as the indirect seasonally adjusted output.