Archive:Sample size and non-response - quarterly statistics
Data extracted in November 2020
Planned article update: January 2021
Highlights
During the first quarter of 2020, as a consequence of the COVID-19 outbreak, the data collection (i.e. interviews) for the European Labour Force Survey (EU-LFS) has been severely hampered in most countries. This resulted in a sharp increase in unit non-response, especially in the last month of the first quarter of 2020 (i.e. March 2020), and consequently in a reduced achieved sample size. The lower participation rate in the survey also led to an increase in sampling errors, that adversely affect the precision of the estimates.
In this context, this article assesses the quality of the data gathered through the EU-LFS for the European Union (EU) as a whole, for each EU Member State individually, as well as for the United Kingdom, two EFTA countries (Norway and Switzerland) and four candidate countries (Montenegro, North Macedonia, Serbia and Turkey). The analysis is based on data and information available up to 10 September 2020. Data for the first quarter of 2020 is mainly compared with data for the first quarter of 2019 (for sample size and sampling errors) in order to avoid comparability issues and bias due to seasonality. Regarding unit non-response, a comparison with annual averages for previous years is also included. Please note that this procedure is legitimate since unit non-response is usually not particularly affected by seasonality and therefore quite stable throughout the year.
This article is part of the online publication Labour market in the light of the COVID-19 pandemic - quarterly statistics along with the articles Labour market slack - unmet need for employment and Hours of work.
Full article
Drastic increase in the unit non-response rate in the first quarter of 2020
The unit non-response occurs when no data are collected about a population unit (usually a person or a household) designated for data collection. Consequently, the unit non-response rate is the ratio of the number of units for which data has not been collected to the total number of units designated for data collection (sampling frame).
Since the beginning of the time series (2011), the unit non-response rate smoothly increased at EU level (see Figure 1). The same conclusion can be drawn when all countries carrying out the European Labour Force Survey (EU-LFS) are considered. However, between the year 2019 and the first quarter of 2020, the unit non-response rate sharply increased at EU level: from 24.7 % in 2019 to 31.9 % in Q1 2020 (+7.2 percentage points). This can be explained by the lockdown measures adopted by most Member States during the first quarter of 2020 to cope with the COVID-19 pandemic. Face-to-face (CAPI (Computer Assisted Personal Interviewing) and PAPI (Paper and Pencil Interviewing)) data collection methods have been stopped and replaced as much as possible by remote collection methods (CATI (Computer Assisted Telephone Interviewing) or CAWI (Computer Assisted Web Interviewing)). Unit non-response mainly increased due to phone numbers or email addresses which were not always immediately available. The growth is slightly weaker when all EU-LFS participating countries are considered: from 27.8 % in 2019 to 32.2 % in Q1 2020 (+4.4 percentage points).
Even if a sharp increase between the year 2019 and the first quarter of 2020 can be seen at EU level, the situation is quite difference across countries. In Bulgaria, Ireland and the United Kingdom, the unit non-response rate increased by around 10 percentage points (12 p.p., 9 p.p. and 9.5 p.p. respectively). Belgium, Czechia, Greece, France, Latvia, Hungary, Malta, Portugal, Slovenia, North Macedonia, Serbia and Turkey also recorded a significant rise in their unit non-response rate (rise between 3.5 p.p. and 7.2 p.p.) (see Figure 2). All these countries broadly used face-to-face interviewing techniques (CAPI and PAPI) for the EU-LFS data collection. By contrast, countries relying exclusively on CATI and CAWI techniques did not perceive a big impact on their unit non-response rate between the year 2019 and the first quarter of 2020. Denmark and Finland saw their unit non-response rate increased by 1.0 p.p. and 1.8 p.p. respectively. In Luxembourg (-4.3 p.p.), Sweden (-0.2 p.p.), Norway (-0.3 p.p.) and Switzerland (-1.0 p.p.), the unit non-response rate decreased.
<sesection>
Sample size decreased starting from the 10th week of 2020
The EU-LFS is based on the uniform sample distribution of the quarterly sample over all the reference weeks of the quarter. This means that the size of each weekly sample corresponds to the size of the total quarterly sample divided by the number of weeks in the quarter (generally 13).
The distribution of the achieved sample size in Q1 2020 is similar to Q1 2019 for the first 9 weeks of the year. The weekly difference in the collected sample between both years is on average around 4 000 individuals for a total situated between 75 000 and 85 000 individuals (see Figure 3). From week 10, the difference between the two years increased to 12 000 in week 10, and even to 14 000 in weeks 11 and 12. In week 13, the difference between the two years narrowed to around 7 000 individuals.
These numbers reflect the lockdown measures taken by the governments of several EU Member States in the first quarter of 2020 from week 10 onwards. The achieved sample size shows a decrease from week 10 due to restrictions in surveys data collection. Then, after countries adopted measures to increase the survey participation (like the use of additional information to reach people selected in the sample: such as telephone numbers or email addresses from registers of mobile phone or landlines numbers and tax databases), the achieved sample size increased again.
_.png)
In the first quarter of 2020, many countries reported a reduction in the sample size collected in weeks 10-13 compared with weeks 1-9 (see Figure 4). Only six EU Member States (Finland, Malta, the Netherlands, Estonia, Croatia and Luxembourg) had a bigger average weekly sample in weeks 10-13 than in weeks 1-9.
At EU level, the ratio of the average weekly number of people interviewed in the weeks 10-13 to the average weekly number of people interviewed in the weeks 1-9 in 2020 was 89.8 %, while it was 99.1 % in 2019. This corresponds to a decrease of nearly 10 percentage points.
The situation was particularly critical in Bulgaria, where the ratio of the average weekly sample size in the weeks 10-13 to the weeks 1-9 was 56 % in 2020, being 99 % in 2019. Slovenia also recorded a ratio less than 60% in 2020 (55 %) but the difference with its ratio in 2019 (75 %) is smaller. The decrease in the average weekly sample size is also noticeable in Ireland and Latvia, with a ratio of average sample size in the weeks 10-13 to the weeks 1-9 less than 80 % in 2020 (74 % in Ireland and 78 % in Latvia) and close to 100% in 2019 (98 % in Ireland and 97 % in Latvia).
Slight increase in sampling errors in Q1 2020 figures
The estimates produced by the EU-LFS are subjected to specific precision requirements specified in the Council Regulation (EC) No 577/1998, which establishes the organisation of the survey. In particular, specific requirements are defined concerning the reliability of estimates on the number of employed and unemployed. The coefficient of variation (CV) for the employed and unemployed population, as an indicator of the precision of the EU-LFS estimates, is transmitted by countries to Eurostat on a quarterly basis.
As can be seen from Figure 5, the COVID-19 crisis also had an impact on the precision of the measurement of employment and unemployment. Almost all countries show a deterioration in the accuracy of the estimates for both employment and unemployment between the first quarter of 2019 and the first quarter of 2020. This deterioration is linked to the continuous increase in the unit non-response (already visible in previous years), which reduces the achieved sample size, especially in the specific segment of the population attached to the labour market, and also to an additional increase in greater intensity coming from the COVID outbreak.
The loss of precision in Q1 2020, compared with Q1 2019, mostly affects Bulgaria, Greece, Spain, Italy, Romania and Sweden for both estimates on employment and unemployment. Among the non-EU countries, Norway and Switzerland also recorded a significant loss of precision for both estimates in Q1 2020 compared with Q1 2019. In addition, Croatia, Cyprus and the Netherlands are affected by a loss of precision for the unemployment estimates.
Source data for tables and graphs
Data sources
All figures in this article are based on quarterly results from the European Labour Force Survey (EU-LFS).
Source: The European Union Labour Force Survey (EU-LFS) is the largest European household sample survey providing quarterly and annual results on labour participation of people aged 15 and over as well as on persons outside the labour force. It covers residents in private households. Conscripts in military or community service are not included in the results. The EU-LFS is based on the same target populations and uses the same definitions in all countries, which means that the results are comparable between countries.
European aggregates: EU refers to the sum of EU-27 Member States. If data is unavailable for a country, the calculation of the corresponding aggregates takes into account the data for the same country for the most recent period available. Such cases are indicated.
Country note: Due to technical issues with the introduction of the new German system of integrated household surveys, including the Labour Force Survey (LFS), the figures for Germany for the first and second quarter of 2020 are not direct estimates from LFS microdata, but based on a larger sample including additional data from other integrated household surveys. A restricted set of indicators has been estimated and used for the production of the LFS Main Indicators. These estimates have also been used in the calculation of EU and EA aggregates, and are published for some selected indicators (estimates for Germany are flagged as p – provisional, and u – unreliable). For more information, see here.
Definitions: The concepts and definitions used in the EU-LFS follow the guidelines of the International Labour Organisation.
Data collection techniques: The different kinds of data collection techniques used in the LFS are the following:
1) PAPI (Paper and Pencil Interviewing): PAPI is a face-to-face interviewing technique in which the interviewer enters the responses into a paper questionnaire. If no interviewer is present and respondents enter the answers themselves it is considered a self-administered questionnaire.
2) CAPI (Computer Assisted Personal Interviewing): CAPI is a face-to-face interviewing technique in which the interviewer uses a computer to administer the questionnaire. Responses are directly entered into the application, and control and editing can be directly performed.
3) CATI (Computer Assisted Telephone Interviewing): CATI is a telephone surveying technique in which the interviewer follows a questionnaire displayed on a screen. Responses are directly entered into the application. It is a structured system of interviewing that speeds up the collection, control and editing of information collected.
4) CAWI (Computer Assisted Web Interviewing): CAWI is an Internet surveying technique in which respondents follow a questionnaire provided on a website and enter the responses into the application themselves
Five different articles on detailed technical and methodological information are linked from the overview page of the online publication EU Labour Force Survey.
Context
The COVID-19 health crisis hit Europe in January and February 2020, with the first cases confirmed in Spain, France and Italy. COVID-19 infections have now been diagnosed in all European Union (EU) Member States. To fight the pandemic, EU Member States have taken a wide variety of measures. From the second week of March, most countries closed retail shops apart from supermarkets, pharmacies and banks. Bars, restaurants and hotels have also been closed. In Italy and Spain, non-essential production was stopped and several countries imposed regional or even national lock-down measures which further stifled the economic activities in many areas. In addition, schools were closed, public events were cancelled and private gatherings (with numbers of persons varying from 2 to 50) were banned in most Member States.
The large majority of the prevention measures were taken during mid-March 2020 and most of the prevention measures and restrictions were kept for the whole of April and May 2020. The first quarter of 2020 is consequently the first quarter in which the labour market across the EU has been affected by COVID-19 measures taken by the Member States.
Employment and unemployment as defined by the ILO concept are, in this particular situation, not sufficient to describe the developments taking place in the labour market. In this first phase of the crisis, active measures to contain employment losses led to absences from work rather than dismissals, and individuals could not search for work or were not available due to the containment measures, thus not counting as unemployed.
Direct access to