The Monthly Services Index (MSI) monitors short term trends in output of enterprises in the non-financial traded services sector. From January 2022, output is measured in current prices (turnover) and in constant prices (volume index) for each sector, where the value of turnover is deflated by price changes within each sector.
The sample size is approximately 2,250 enterprises. The sample comprises a census of all enterprises with an annual turnover value of more than €20m or enterprises with more than 100 persons engaged. The remainder of the target population is stratified using 2-digit Statistical Classification of Economic Activities in the European Community, i.e. NACE Rev. 2 classifications. Each of these 2-digit NACE sectors are further subdivided into strata based on turnover. A simple random sample is then drawn from each stratum. Retail and Motor Trade figures are taken from the separate Retail Sales Index sample of approximately 1,600 enterprises.
The response rates for the provisional results are typically 46% in terms of the enterprises surveyed which represents 75% of the value of total turnover. The corresponding figures for the final results are 55% and 83% respectively. These response rates are based on averages for the 6 month period ending December 2018.
The business activity classifications used in this statistical release are based on the Statistical Classification of Economic Activities in the European Community i.e. NACE Rev. 2.
The index system is structured on the non-financial traded services sector covered in the 2015 Annual Services Inquiry (ASI). This non-financial traded services sector is further broken down as follows:
To compile the MSI, each of the above published NACE sectors is separated into three distinct cell sizes based on the constituent enterprises’ reported gross value added (GVA) for 2015. Using data taken from the 2015 ASI, GVA baseweights are then calculated for each of these cells and the baseweights are updated each month using a matched sample approach.
An enterprise’s monthly GVA value is calculated as follows: respondents report their monthly turnover figures which are transformed into estimated GVA figures by applying a firm specific factor based on an individual respondent’s 2015 ASI return. The factor is calculated for each firm by simply dividing their estimated GVA by reported turnover. If an enterprise was not on the ASI sample then the relevant cell mean GVA/turnover ratio, calculated from the 2015 ASI, is applied. The reason for this methodology is to reduce the disproportionate impact that some enterprises (which report large turnover figures but have a relatively small GVA) can have on the overall series.
For further information visit the Methods area on the CSO website.
Monthly and annual percentage changes are calculated before rounding. All indices presented in the tables are rounded to one decimal place.
Seasonal adjustment for each of the sectors is conducted using a direct seasonal adjustment approach. However, the overall MSI is estimated using the indirect approach, i.e. the MSI is derived by adding the weighted seasonally adjusted sub-components. The main reason for adopting the indirect approach for the MSI is to attribute the monthly and annual changes in the MSI to each of its sub-components. Seasonal adjustment models are developed for each series based on unadjusted data spanning from January 2009 to the current period. These models are reviewed on an annual basis; however seasonal factors are updated each month. Following an annual review of seasonal adjustment models in May 2021, all sub-indices were found to display seasonal factors.
The seasonal adjustment of the MSI is conducted using the X-13ARIMA-SEATS software produced, distributed and maintained by the U.S. Census Bureau. The seasonal estimates take into account other factors that may impact on the quality of the seasonal adjustment, i.e. outliers, temporary changes and level shifts.
For additional information on the use of X-13ARIMA-SEATS see (Findley, D.F., B.C. Monsell, W.R. Bell, M.C. Otto, and B. Chen (1998), “New Capabilities and Methods of the X-12-Arima Seasonal Adjustment Program”, Journal of Business & Economic Statistics, 16, pp. 127-177.) and Win X-13
The rebasing of the series is in line with EU recommendations to update the base reference periods at regular five-year intervals. This new series replaces the existing series to base year 2010 as 100.
The difference in the new rebased MSI series is the use of new cell and sector baseweights taken from the ASI 2015. The existing cell structure/breakdown was maintained in this series. For each sector, enterprises are placed in a particular cell based on the following criteria and each sector is then weighted to compile the overall index:
The new baseweights are updated each month using changes to respondents’ monthly estimated GVA.
Learn about our data and confidentiality safeguards, and the steps we take to produce statistics that can be trusted by all.