Contact infoLabour and Income, Social Statistics
Daniel F. Gustafsson
+45 39 17 35 89
Get as PDF
The Labor Force Survey (LFS) has been conducted since 1994 and tables can be found at StatBank Denmark from 1996 onwards. A new enumeration method has been introduced, where the sources only go back to 2008. The new series therefore only go back to 2008 in comparable form. LFS is made according to the same guidelines in all EU countries and several other countries and is therefore well suited for international comparisons.
Comparability - geographical
The Labour Force Survey is the Danish contribution to the European Labour Force Survey. Topics, categories, definitions and so on are laid down by the European Union which makes the surveys suitable for both overall and very specific international comparisons of labour market issues.
Many countries outside the EU also carry out similar Labour Force Surveys. This means that the Danish Labour Force Survey is the best Danish survey for international comparisons of labour market statistics.
Harmonized overview of variables used for reporting data: - Codification
Comparability over time
In the second quarter of 2023 changes have been made to the questionnaire which simplifies the way information on desired working hours is collected. From Q2 a person is asked directly whether they want to work more, less or an unchanged number of hours compared to the time they normally work. The transition from Q1 to Q2 2023 will thus be affected by data break.
In 2022q1, a new stratification was introduced in the LFS. Register data on employment and register unemployment are utilized to a greater extent, in order to obtain a greater number of responses in some of the groups that suffer from low response rates. For starters, the population is divided into four groups: 1) in stable employment, 2) in registered unemployment, 3) neither in stable employment nor registered unemployment and 4) persons aged 75 to 89. In addition, groups 1 and 3 are divided into the age groups 15-29, 30-64 and 65-74. This results in eight different strata, which are used in the sample selection from 2022q1 onwards. As the LFS consists of four panels, each appearing for six quarters, there will be a gradual implementation of the new stratification until 2023q2.
New regulation in the LFS from 2021 From January 1st 2021 the LFS is adapted to a new EU framework regulation Regulation 2019/1700. The new regulation applies to all EU countries and is introduced simultaneously throughout the EU by the 1st of January 2021. The new regulation entails changes in definitions of some variables and in the order in which the questions are asked. In addition a number of new variables are included at the same time as other variables are removed. One of the more significant changes concerns temporary / long-term absence, which means that persons who, for certain reasons of absence are completely absent from work and where the absence has lasted or will last for three months or longer and are not receiving a salary or unemployment benefit beyond the three months are not counted as employed.
Questionnaire 2021 Until the year 2020 the LFS has been collected at the individual level for 15-74-year-olds. From 2021 the population has changed to also include the age group from 75-89 years. On a quarterly basis the sample has thus increased from 34,320 people to 36,020 people.
The new weighting scheme has also been changed to also include the age group 75-89 years. For both the age group 65-74 year olds and 75-89 year olds it applies that so far they are only reported to (and published by) Eurostat and are not included in the national dissemination via http://www.Statbank.dk.
1984 was the first time Denmark started a large survey on the population's labour market status. Though, it was conducted only once a year during spring time. In 1994 the Labour Force Survey was established as we know it today. From this time the survey has been conducted continuously every day all through the year. In 2000 the questionnaire was changed significantly, however the changes did not affect the main indicators such as the number of employed, unemployed and outside the labour force. The slight adjustment in the weighting in 2003 is currently reviewed as to the possible effects on comparability.
In 2007 the survey was changed and expanded considerably, by expanding the quarterly sample size from around 20,000 to 40,532 in order to reduce sampling errors of survey results. Furthermore the rotation pattern was changed from three to four waves, and the data collection process which Statistics Denmark had been in charge of so far was outsourced. The changes in 2007 resulted in a break in series both on detailed sub-groups. As a result of this one should be aware of this when comparing results before and after the break.
In 2011 the weighting scheme was adjusted when auxiliary information on age and educational level was crossed in order to improve the estimates on educational level. All figures back to 2007 were revised. The central difference to all previous weighting schemes considering comparability is that the weighting now has a target population of 15-64 years. Before the target population was 15-66 years.
See more about weighting methods here.
Starting with Q3 2010 the main figures of the Danish LFS are seasonally adjusted. The main figures are: Employed, unemployed and persons outside the labour force, giving the general labour market attachment of the population. The series go back to Q1 1996, and the entire period is used for the seasonal adjustment. The program used is X-12-Arima, and logarithmic transformation is applied on all three series. Only aggregate levels are seasonally adjusted. The figures for the entire labour force are not directly seasonally adjusted. From Q1 2012 it has been decided in the series for unemployed to model Q1 2009 as a level change or outlier. This was due to the economic crisis. This has resulted in minor changes to the seasonally adjusted figures for the following quarters. The decision was taken based on our knowledge of the developments since Q1 2009 and on concrete statistical tests. Outlier-modelling is a technical adjustment that secures a better estimation of the seasonal pattern - the overall level of the seasonally adjusted series is unchanged.
Before 2016 individuals who had research protection were not interviewed, but this protection has been removed from the first quarter of 2016. This effectively means an expansion of the sample for which compensated by reducing the number of people who are drawn out to the first panel from 10,133 persons to 8,580. The total quarterly sample will in the long term be reduced from 40,532 to 34,320 people. A series of tests on this show, however, that it does not appear to have influenced the figures for the labor market participation.
The LFS unemployment has been revised from Q3 2015 due to an error in the number of gross unemployed recipients of social assistance, but the error only has a minor effect on the LFS unemployment.
From the first quarter of 2016 the LFS was conducted by a different data collector and which caused a low response rate. From the first quarter of 2016 is it also possible to answer the survey online instead of just on the phone as before, so to improve the web-solution some changes were also made in the online version of the survey. In addition, the sample was changed since protection research is removed. These changes have resulted in a significant break. The employment is increased and the number of people outside the labourforce has decreased. The LFS unemployment is only affected to a lesser extent. Read more about the Data Break16(in Danish). The changes have an effect on a large number of variables in the LFS, and one should be very careful to make comparisons between the figures for the first quarter of 2016 for previous quarters.
From the first quarter of 2017 the LFS was conducted by a different data collector and the response rate has increased. This change has resulted in a significant break which is explained here: Data Break17(in Danish).
Uninterrupted time series based on LFS data can generally be traced back to 2008, and time series longer back in time be traced back without break. The historical data for LFS for the period from 1996 to Q1 2019, with the old enumeration, can be found in archive tables. In these, there are data breaches between 2015 and 2016 and again between 2016 and 2017.
Read more about time series, that have been analyzed more in-depth, and short presentations of i.e. the employment series, unemployment series and the working time series and descriptions of the developments and breaks in the Time Series.
In 2022q1, a new stratification was introduced in the LFS. Register data on employment and register unemployment are utilized to a greater extent, in order to obtain a greater number of responses in some of the groups that suffer from low response rates. Employment and unemployment are now only somewhat affected by the special circumstances caused by COVID-19, so the whole COVID-19 period can now be treated more comprehensively in the seasonal adjustment. Therefore, the time series for seasonally adjusted employment, unemployment and persons outside the labor force have been reviewed from 2019q1 onwards. COVID-19 may have affected the composition of the respondents in the data collection for the Labor Force Survey (LFS), and it remains to be analyzed whether there is a need to methodologically correct for a possible bias in the figures under COVID-19.
Changes in variables for Q3 2022: REGISTER is now produced only using register information. In the past, we asked everyone if they were registered at the unemployment center – in order to capture people that were registered and not receiving benefits. This was unnecessary, as only persons receiving benefits are registered at the unemployment office. This change leads to a better cohesion between the actual registers and the LFS variable REGISTER.
WANTREAS is now automatically coded as 6 for pensioners. In order to reduce the burden on respondents, we do not ask persons receiving age-related pensions about the reason for not wanting to work. Instead, we automatically assign the value ‘6 – Retirement’.
Changes in variables for Q1 2023: As a result of the new maternity legislation, there is no longer an explicit distinction between maternity leave and parental leave. This has meant that information about this has to be collected in a different way. A question has been introduced in the LFS about the child's age, specifically whether the child has not yet been born, is under ten weeks old or over ten weeks old. If the child is not born or is less than ten weeks old, the parent is automatically classified as being employed if the person was otherwise employed before the maternity leave. If, on the other hand, the child is over ten weeks old, the parent is employed if he or she receives wages during maternity leave or if the length of the maternity period does not exceed three months.
Coherence - cross domain
The Register of Labour Market Statistics, Unemployment The most used unemployment statistics in Denmark is registerunemployment, which is based on the information from every public employment office and unemployment insurance funds in Denmark. The purpose is to measure the number of unemployed people who are receiving social benefit. RAM measures the number of unemployed people in full-time equivalents (FTE's). This means that part-time unemployed for example a person with a small job, who also receives complementary unemployment benefit from the local job-centre under the Danish Social Assistance Act is calculated as a certain percentage of a full-time unemployed. A half-time unemployed person will for example count as ½ FTE unemployed. In the Labour Force Survey, people are defined as employed if they have worked for at least one hour in the reference week. A person, who works 15 hours a week and who also receives supplementary unemployment benefit will be defined as employed in the Labour Force Survey. In RAM-unemployment statistics this person will be included in the group of unemployed people, because the supplementary unemployment benefit reflects registration as unemployed at a public employment office. The difference between unemployment in the Labour Force Survey and the Register of Labour Market Statistics is described in detail here. The issue whether or not a person has to be registered as unemployed at a public employment office to be considered unemployed or not is a distinct difference between the Labour Force Survey and RAM. The Labour Force Survey does not require any payment of social benefits. This is because of the different labour market models around Europe. Not all countries have a policy, where people register themselves when unemployed. For the sake of international comparison, the important issue is therefore whether or not people have been working or not, not whether people are registered or not in the LFS. According to the Danish Labour Force Survey, only around half of the unemployed persons are receiving unemployment benefit. The other half consists of students looking for work and people who are actively looking for a job and declare that they can start a job within two weeks, although they are not registered as unemployed. At the same time some of the persons included in the RAM unemployment statistics are not considered unemployed in the Labour Force Survey. For example people, who do not actively look for a job and/or who are not able to start a job within two weeks. If people do not meet these criteria they are defined as outside the labour force or employed regardless if they are registered at a public employment office or not. Due to the different definitions of unemployment, the results from RAM and the Labour Force Survey vary.
Find more information on registered unemployment.
Other employment statistics Register based-labour force statistics (RAS): Both the Labour Force Survey and RAS examine the population´s labour market status. The Labour Force Survey is based on interviews, while RAS is based on administrative sources - among others the e-income register, the work place register, the central business register, the register with information about persons without ordinary employment, the educational register and the population register. Due to the fact that it takes time to gather information from several of the administrative registers the data processing time is a bit more than a year for RAS. This means, that information on people registered as full time unemployed in November 2005 will be published in the spring of 2007. The Statistics are scheduled to be published within 16 months after the end of the reference year. The degree of consistency between the Labour Force Survey and RAS is usually high with respect to the key results, for example the number of employed and unemployed people in Denmark. However, for some variables for example - full-time/ part-time employees - significant differences appear. This is due to completely different compilation methods. Some information on the population's labour market relations is better collected by RAS than by the Labour Force Survey, because RAS's base is the total population, whereas the Labour Force Survey is based on a sample size of the population. In a sample, small groups - like immigrant groups - can be unreliable due to too high sampling error. In these areas RAS is a good substitute. However, if the wish for example is to know the number of part-time employees who would like to work full-time; how many people work at home regularly; or how many people have found their job with the help of a public employment office, the Labour Force Survey is the best statistics, because RAS does not measure the subjective wants and wishes of individuals.
Read more about [RAS]https://www.dst.dk/en/Statistik/emner/arbejde-og-indkomst/befolkningens-arbejdsmarkedsstatus/arbejdsmarkedsstatus-ras-register Read more about Employment. Read more about Concepts and Employment i LFS and other Danish statistics. Read more about working time accounts ATR and full-time employees BFL.
Coherence - internal
Nothing to add, since the basic data of the LFS is collected through surveys and therefore there is consistency in the questionnaire regarding the individual variable.