Background

A new Labour Force Survey (LFS) was introduced by the CSO with effect from Q3 2017 which replaced the Quarterly National Household Survey (QNHS). Detailed information on the background to this change is available from the following Information Note:

Information Notice - Labour Force Survey Quarter 3 2017

From Q1 2018, additional adjustments have also been made to the historic region, occupation and education series to further enable comparability with the new LFS for these indicators. 

In addition, as a result of regulation changes, the NUTS regions used in the LFS have changed with effect from Q1 2018 and as a result the existing series from Q1 2012 to Q4 2017 has also been reweighted to account for these new groupings.

Inclusion of additional indicators in the back-casting methodology

Variables included in back-casting in Q3 2017

As detailed in the information note above, the CSO worked to minimise the breaks in series to the key survey estimates by back-casting the QNHS series from Q2 2017 to Q1 1998. These back-cast series were created using scaling factors from a comparison of data captured from a parallel run of the QNHS and LFS at the beginning of 2017.

This enabled comparability of the back-cast series with the LFS series for the following main indicators:

•  ILO status (Employed, Unemployed, Inactive) by sex (Male and Female) and by age (15-24 years and 25+ years)

•  NACE Rev. 2 groups (table 2 of the LFS release) by sex (Male and Female)

Additional variables included in back-casting in Q1 2018

To further enhance the comparability of the new and old data series, the CSO has now extended the back-casting solution used to manage the transition from the QNHS to the LFS to include the following indicators:

•  NUTS3 Regions (pre-Q1 2018 groupings) by Labour Force ILO status (Employed and Unemployed)

•  Occupation groups (table 4 of the LFS release);

•  Highest level of education completed (supplementary table 8 of the LFS release) by sex (Male and Female).

Impact on existing Labour Market estimate

The previously published estimates for the series which were already controlled for in the back-casting solution in Q3 2017 are not impacted by the addition of these three series;

•  All regional data has been revised from Q2 2017 to Q1 1998 based on the NUTS3 regional classification which was used until Q4 2017;

•  The classification system for occupations was last updated in Q1 2007 with the result that there was a break in series from that point in time. As a result, the previously published series for occupation groups has now been revised from Q2 2017 to Q1 2007. This revision enables comparability of occupation group data from Q1 2007 to date;

•  The underlying classification for the education attainment series was last updated in Q1 2014 and consequently there is a break in series from that point in time. The educational attainment series has therefore  been revised from Q2 2017 back to Q1 2014 and this revision enables comparability of educational attainment data from Q1 2014 to date.

Final variables included in the LFS back-casting methodology

The table below details the full list of indicators that are now included in the back-casting solution as of Q1 2018. It should be noted that there may be changes in the levels of other series not included in this solution from Q3 2017 onwards. Consequently, such series before and after the introduction of the LFS may not be comparable and users should therefore note this when examining annual and quarterly changes.

Revisions to composition of NUTS Regions

The NUTS boundaries were amended on 21^st November 2016 under Regulation (EC) No.2066/2016 and took effect from 1^st January 2018. Please see http://ec.europa.eu/eurostat/web/nuts/history for further details.

As a result, new NUTS (regional classification) groupings have been introduced for Ireland. At NUTS3 level, County Louth has moved from the Border to the Mid-East region and what was formerly South Tipperary has moved from the South-East to the Mid-West Region. At NUTS2 level, the change sees the number of regions increase from two to three. Please see Appendices I and II for the new and old classifications.

As the CSO weights results in the LFS using NUTS3 groups, survey estimates have been revised to take account of these changes. While the above regulation requires Ireland to revise survey estimates from Q1 2013, the CSO has further extended the revision to Q1 2012. This reweighted data is published with the Q1 2018 results and users should note that there is a break in the regional data series from Q1 2012 as the results for the period Q1 1998 to Q4 2011 are published using the old NUTS groupings.

It can be noted that the regional reweighting does not have a significant impact on the headline indicators previously published.

Summary of changes

The new LFS, which has been introduced in Q3 2017, is the most significant change to Labour Market statistics in Ireland since the introduction of the QNHS in Q4 1997. This modernisation is a critical component of the CSO’s strategy to continue to deliver high quality household statistics for Ireland.

The CSO is committed to working with users to minimise the disruption arising from the new survey and it is hoped that the addition of the region, occupation and education variables to the back-casting of the QNHS will further enhance the comparability of the data series from before and after the introduction of the new LFS. 

Finally it should be noted that as the addition of these variables to the back-casting list brings with it a further increase in complexity, it will not be possible to add any further variables to this list and it is therefore not intended to further revise the back-casting methodology.