Study: EU-LFS 2004
Titles
Title
European Union Labour Force Survey 2004
Abstract
EU-LFS 2004 contains the Module on Work organisation and working time arrangements.
The study group consisted of employed persons, the self-employed, employees and unpaid family workers.
Coverage
Geographical Coverage
The EU-LFS 2005 covers "the [then] 25 Member States of the Union. In addition the survey covers member states of the EEA, Iceland and Norway, Switzerland by bilateral agreement, as well as the Candidate Countries, Bulgaria, Croatia, Romania and Turkey." (Eurostat (2006): Quality report of the European Union Labour Force Survey 2004, p. 2).Turkey and Malta are not included in the micro-data.
Time Period Covered
The reference week is one week in each quarter starting on Monday and ending on Sunday. In all countries but Germany, Hungary (3 weeks/month), Bulgaria, Croatia and Turkey the sample is spread over the 13 weeks of the quarter. [...] The first week of a year or quarter is defined as the week that includes the first Thursday of the year or the quarter." (Eurostat (2006): Quality report of the European Union Labour Force Survey 2004, p. 4.)
DOIs
Resources
-
Country Specific Information: EU-LFS 2004
LV - Latvia
National Reference
Producer
Central Statistical Bureau of Latvia
Universe
All persons aged 15 to 74 years who are permanently resident in Latvia.
Sampling Procedure
Source Of Sampling Frame
Population Census 2000, Population Register, statistical register of dwellings, statistical register of households
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Households
Stratification Criteria
Region, urban/rural
Panel Design
Number Of Rotational Groups
3
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
41.35 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The initial weights are calculated according to the sample design, with all persons within the same PSU having equal design weights. The design weights are adjusted using the data of response level in each PSU.
Coverage Adjustment Weight: Method
These weights are then adjusted on the basis of demographic data. Demographic data are broken down by degree of urbanisation, age groups and sex for adjustment of the quarterly weights. For adjustment of the yearly weights demographic data are broken down by degree of urbanisation, age groups and sex as well as in NUTS 3. All persons within the same household have equal initial weights, but the final weights tend to be diverse.
LU - Luxembourg
National Reference
Corresponding National Study
Erhebung über Arbeitskräfte
Producer
infas Institute for Applied Social Sciences
Universe
Persons registered as residing in one of the Luxembourgian communes.
Sampling Procedure
Source Of Sampling Frame
Central Population Register
Sampling Design
Probability
- random
- stratified
- one stage
Primary Sampling Units
Households
Secondary Sampling Units
Not used
Stratification Criteria
Cantons, households size classes (1,2,3,4+)
Panel Design
Number Of Rotational Groups
2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
51.45 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Coverage Adjustment Weight: Method
A calibration is performed with CALMAR macro of INSEE-France for correcting the non-response at the household level. Among many variables like region, household class size, age of reference person and citizenship of reference person, it should be found out, by logistic regression, by how much they account for the non-response phenomen. The variables canton, size of household, and age of the reference person are selected. Three regions are determined by grouping some cantons. The final adjustment consists of making the most recent distribution of sex * age class * citizenship in the population agree with the distribution of the same variables in the set of respondents. This calibration is implemented at the person level.
LT - Lithuania
National Reference
Producer
Statistics Lithuania
Universe
All persons usually living in the households of the selected dwellings, including those who are temporarily abroad for a period of less than a year.
Sampling Procedure
Source Of Sampling Frame
Population Register
Sampling Design
Probability
- random
- not stratified
- one stage
Primary Sampling Units
Individuals
Secondary Sampling Units
Not used
Panel Design
Number Of Rotational Groups
4, 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
45.21 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The initial household design weights are calculated, taking into account the unequal selection probabilities of the households.
Coverage Adjustment Weight: Method
These are then adjusted by the use of auxiliary information relating to population data on 10 NUTS-3 (counties) and the intersection of 13 age-groups, sex and urban/rural as well as data from the National Labour Exchange on the number of registered unemployed persons.
HR - Croatia
National Reference
Corresponding National Study
Labour Force Survey
Producer
Republic of Croatia; Central Bureau of Statistics
Universe
The target population comprises all persons living in private households who usually reside in Croatia or intend to stay in Croatia for at least 12 months.
Sampling Procedure
Source Of Sampling Frame
2001 Populatin Census
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Dwellings
Stratification Criteria
Counties, city of Zagreb
Panel Design
Number Of Rotational Groups
0 (no sample unit is carried over from previous years)
Data Collection
Type Of Data Source
Survey
Percentage Of Proxy Interviews
35.56%
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of Selection Probability
Non-response Weight: Method
The non-response weights are calculated using the weighting classes method. There are 57 weighting classes. In Croatia, municipalities are officially divided into two goups, according to the level of urbanisation. Weighting classes are 17 city quarters in City of Zagreb, and, in each of 20 counties, two groups of two types of municipalities.
RO - Romania
National Reference
Producer
National Instititue of Statistics Romania
Universe
Persons resident in Romania.
Sampling Procedure
Source Of Sampling Frame
Census 2002
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census sections
Secondary Sampling Units
Dwelling clusters
Stratification Criteria
Region, urban/rural
Panel Design
Number Of Rotational Groups
4; 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
27.91 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The responding dweling units are categorised by the characteristics county (NUTS 3) and urban/rural residency.
Coverage Adjustment Weight: Method
The weights are calibrated to the best latest available population totals by region/urban-rural residency, gender, age groupds and the household totals by region, using the SAS macro Calmar. The totals known at population level from current demographic statistics are based on the 2002 Population Census.
NO - Norway
National Reference
Producer
Statistics Norway
Universe
The resident population is the de jure one based on the Central Population Register.
Sampling Procedure
Source Of Sampling Frame
Central Population Register
Sampling Design
Probability
- random
- stratified
- one stage
Primary Sampling Units
Households
Secondary Sampling Units
Not used
Stratification Criteria
County (NUTS-3)
Panel Design
Number Of Rotational Groups
8
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Register,Survey
Percentage Of Proxy Interviews
13.76 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The initial weights are adjusted by post-stratification according to sex, age groups and employment status, altogether 96 post-strata. The variables used for post-stratification are based on information from the Central Population Register, the Register of Employees and the Tax Register.
Coverage Adjustment Weight: Method
The post-stratification adjusted weights are calibrated within each of the 19 counties (NUTS-3 level), with respect to the marginal totals of the same auxiliary variables. The expansion factors are calculated according to the population totals aged 16-74.
HU - Hungary
National Reference
Producer
Hungarian Central Statistical Office
Universe
Persons living in the private households in Hungary, included are also household members temporarily absent or living abroad if they have common income/consumption with the surveyed household.
Sampling Procedure
Source Of Sampling Frame
2001 Population and Housing Census
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Dwellings
Stratification Criteria
Administrative units, size categories of localities
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
42.67 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
For any stratum of the sample, the unique design weight is defined as the ratio of the total number of dwellings in the stratum to that in the sub-sample for that stratum.
Coverage Adjustment Weight: Method
Calibrated weights are determined with the method of generalised raking. For each of the 20 geographical units, the calibration variables or controls are totals for age-sex groups, total number of household and total resident population in cities with 50 000+ inhabitants. The calibration is organised so that all members in a sample household have the same calibrated weight as that household.
FR - France
National Reference
Corresponding National Study
Questionnaire logement de l’enquête emploi
Producer
National Institute of Statistics and Economic Studies
Universe
Population aged 15+ living in private households on French metropolitan territory.
Sampling Procedure
Source Of Sampling Frame
Population Census of 1999
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Dwellings
Stratification Criteria
French region (NUTS-2) and type of urban unit
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
32.08 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
A correction for non-response is made, using several criteria: size of urban unit, number of rooms in the housing, type of housing, number of new dwellings and region.
Coverage Adjustment Weight: Method
An adjustment is made with the population pyramid by age groups and gender for each independent sub-sample.
BG - Bulgaria
National Reference
Universe
The resident population includes all persons usually residing in Bulgaria, including persons temporarily abroad (less than one year).
Sampling Procedure
Source Of Sampling Frame
2001 Population Census
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Households
Stratification Criteria
Administrative units, urban/rural
Panel Design
Number Of Rotational Groups
4; 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
41.39 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
Data obtained by the survey are post-stratified by 28 districts, urban/rural areas, sex and four age groups. All persons in each of these 488 strata have the same weight.
Coverage Adjustment Weight: Method
The weight is calculated by dividing the population in each stratum by the number of interviewed persons in the same stratum.
BE - Belgium
National Reference
Corresponding National Study
Continuous Labour Force Survey /
Ständige Erhebung über Arbeitskräfte
Producer
Directorate-general Statistics and Economic Information
Universe
Private households, where at least one person is younger than 75.
Sampling Procedure
Source Of Sampling Frame
National Register of Persons
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Households
Stratification Criteria
Region
Panel Design
Number Of Rotational Groups
0
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
22.52 %
Weighting
Design Weight: Target
Person
Non-response Weight: Method
Adjustments for non-response are done using a posteriori stratification by province (NUTS 2), sex and age.
Coverage Adjustment Weight: Method
In each of the post-strata thus obtained, a weight is calculated whose numerator is the population at the middle of the quarter according to the National Register of Persons and whose denominator is the number of usable responses.
DE - Germany
National Reference
Corresponding National Study
The German micro-census /
Mikrozensus
Producer
Statistische Ämter des Bundes und der Länder
Universe
The resident population includes all inhabitants with their main place of residence and their secondary residence in the territory of the Federal Republic living in private and collective households.
Sampling Procedure
Source Of Sampling Frame
1) Census data from 1987: survey base for former BRD. 2) Central population register of the German Democratic Republic: data for former DDR. 3) Register of new dwellings
Sampling Design
Probability
- systematic
- stratified
- one stage
Primary Sampling Units
Dwelling blocks
Secondary Sampling Units
Not used
Stratification Criteria
Region
Panel Design
Number Of Rotational Groups
4
Data Collection
Date of Data Collection
One week in spring
Type Of Data Source
Survey
Percentage Of Proxy Interviews
28.02 %
Weighting
Design Weight: Target
Household
Non-response Weight: Method
A two-stage adjustment procedure is used.
(a) If possible, limited data are collected for households which fail to respond. These data can include: number of members of the household, nationality, and for households comprising only one person: age and sex. From this data, the weightings of respondent households are increased to take account of non-response in the region.
(b) The sample, weighted to take account of non-response, is stratified a posteriori by region, sex, age and nationality and is extrapolated to the population.
DK - Denmark
National Reference
Universe
Persons with domicile in Denmark according to the Central Population Register living in either private or collective households.
Sampling Procedure
Source Of Sampling Frame
Central Population Register and the Unemployment Register (further enhanced with information from the labour market register and the income register).
Sampling Design
Probability
- systematic
- stratified
- one stage
Primary Sampling Units
Individuals
Secondary Sampling Units
Not used
Stratification Criteria
Registered unemployment
Panel Design
Number Of Rotational Groups
3; 2-(2)-1
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Register,Survey
Percentage Of Proxy Interviews
2.68 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The three strata are weighted separately. For Stratum 1) the register-based information age, education and gross income is used to derive initial non-response weights. For Stratum 2) age, gross income and group of industry is used.
After this step weighting is performed by using a combination of sex and mainly 5 years age groups for the 3 sampling strata separately, based on the Population Register.
FI - Finland
National Reference
Corresponding National Study
Finnish Labour Force Survey
Producer
Statistics Finland
Universe
People aged 15 to 74 who are registered as permanently resident in Finland, including those who are temporarily abroad for a period of less than a year, members of the armed forces, and the institutional population. It also includes foreign nationals who have been living in Finland for at least a year.
Sampling Procedure
Source Of Sampling Frame
Total population database, based on the Population Information System of the Population Register Centre
Sampling Design
Probability
- systematic
- stratified
- one stage
Primary Sampling Units
Individuals
Secondary Sampling Units
Not used
Stratification Criteria
Region
Panel Design
Number Of Rotational Groups
5; 3-(1)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Register,Survey
Percentage Of Proxy Interviews
24.77 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The strata are constructed by gender, age and region, totalling 252 cells.
Coverage Adjustment Weight: Method
The post-stratified weights are calibrated according to gender, age group, region, reference week and status in Ministry of Labour's job-seeker register. The register indicator is further divided into three categories according to the length of being unemployed in the register.
IE - Ireland
National Reference
Corresponding National Study
Quarterly National Household Survey
Producer
Central Statistics Office Ireland
Universe
Persons who usually reside on Irish territory living in private households.
Sampling Procedure
Source Of Sampling Frame
Census of Population 2002
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Dwelling blocks
Secondary Sampling Units
Households
Stratification Criteria
Region, urbanisation
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
37.02%
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The survey results are weighted to agree with population estimates broken down by age, sex and region (NUTS 3).
AT - Austria
National Reference
Corresponding National Study
The Austrian micro-census / Mikrozensus
Producer
Statistik Austria
Universe
Persons who have their main residence on Austrian territory during the reference week.
Sampling Procedure
Source Of Sampling Frame
Central Population Register
Sampling Design
Probability
- random
- stratified
- one stage
Primary Sampling Units
Dwellings
Secondary Sampling Units
Not used
Stratification Criteria
Bundesland
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
38.14 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
For each record a basic weight which depends on the stratum is calculated.
Coverage Adjustment Weight: Method
The weights are adjusted in such a manner that the resulting
distribution is in accordance to the population within the federal provinces (Bundesländer). These figures correspond to the population with main residence at the beginning of each quarter minus persons in institutional households calculated by age-, sex- and nationality specific rates based on Census results 2001. The variables which are used for adjusting the data for each Bundesland are age and sex on the one side and nationality on the other side and furthermore household size.
CZ - Czech Republic
National Reference
Producer
Czech Statistical Office
Universe
Persons living in private households, disregarding the type of their stay (permanent, temporary or non-registered).
Sampling Procedure
Source Of Sampling Frame
Register of Census Areas
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Dwellings
Stratification Criteria
Region (districts, Prague 1 district)
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
46.25 %
Weighting
Design Weight: Target
Dwelling
Non-response Weight: Method
The weights are produced by extrapolating a posteriori to the population in 12 age groups, sex and the 77 districts. The demographic figures for individual quarters 2004 were interpolated according to the final result of Census 2001 taking into account the definitive demographic data for end-of-year of 2001 and 2002.
CY - Cyprus
National Reference
Producer
Statistical Service of Cyprus, Ministry of Finance
Universe
Persons who usually reside in Cyprus or intend to stay in Cyprus for at least 12 months.
Sampling Procedure
Source Of Sampling Frame
Population Census of 2001
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Dwellings
Stratification Criteria
Districts, urban/rural
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
35.91 %
Weighting
Design Weight: Target
Dwelling
Non-response Weight: Method
The results are weighted a posteriori to the population households by sex and age groups. No district or urban/rural weighting is carried out.
SE - Sweden
National Reference
Corresponding National Study
Arbetskraftsundersökningen
Producer
Statistics Sweden
Universe
Persons between 15 and 74 who are domiciled in Sweden according to the population register.
Sampling Procedure
Source Of Sampling Frame
Statistics Sweden's Register of the Total Population, Register of the total population, Annual employment register
Sampling Design
Probability
- random
- stratified
- one stage
Primary Sampling Units
Individuals
Secondary Sampling Units
Not used
Stratification Criteria
Sex, county, nationality, employment status
Panel Design
Number Of Rotational Groups
8
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
2.82 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The estimates build on two regression estimators (GREG) with two different types of auxiliary information. The first GREG estimator is used in the estimation of the number of unemployed and subgroups of unemployed. The estimator makes use of auxiliary information from Register of the total population (RTB) and the register of persons seeking work from the National Labour Market Board. The second GREG estimator is used in the estimation of the number of employed and subroups thereof. It makes use of auxiliary information from RTB and the register on employment.
SI - Slovenia
National Reference
Producer
Statistical Office of the Republic of Slovenia
Universe
Persons living in private households and foreign nationals are included, if they correspond to the criteria of household.
Sampling Procedure
Source Of Sampling Frame
Central Population Register
Sampling Design
Probability
- systematic
- stratified
- one stage
Primary Sampling Units
Addresses
Stratification Criteria
Region, urban/rural
Panel Design
Number Of Rotational Groups
5; 3-(1)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
56.88 %
Weighting
Design Weight: Target
Address
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The data are weighted for unequal probability of selection and for non-response and post-stratified according to the known population distribution: age, sex and region (NUTS 3 level). The post-stratification is done on a household level, with members of the same household thus receiving identical weights, and benchmarked to population totals. Institutional population is included in population totals.
SK - Slovakia
National Reference
Corresponding National Study
pracovných síl
Producer
Statistical Office of the Slovac Republic
Universe
Every person aged 15+, living in the household of the selected dwelling without regard to permanent, temporary or unregistered stays.
Sampling Procedure
Source Of Sampling Frame
Census of Population 2001
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Dwellings
Stratification Criteria
NUTS-4
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
60.07 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
Data from the survey for all persons participating in the survey were weighted by administrative data on total population by region, sex and age groups. Extrapolation to the population is done at the level of individuals. The population and the sample are the subject of a post-stratification by NUTS 3 administrative region, sex and age groups.
IS - Iceland
National Reference
Producer
Statistics Iceland
Universe
The resident population comprises persons registered with domicile in Iceland, excluding persons attached to foreign missions and registered persons living abroad for more than six months, but including Icelandic personnel in missions abroad.
Sampling Procedure
Source Of Sampling Frame
National Population Register
Sampling Design
Probability
- random
- not stratified
- one stage
Primary Sampling Units
Individuals
Secondary Sampling Units
Not used
Stratification Criteria
No stratification.
Panel Design
Number Of Rotational Groups
5; 3-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Register,Survey
Percentage Of Proxy Interviews
1.38 %
Weighting
Design Weight: Target
Person
Non-response Weight: Method
The a posteriori stratification variables are age groups and sex.
UK - Great Britain
National Reference
Producer
UK Office for National Statistics
Universe
Persons living in private households, including persons who are temporarily absent. In Great Britain, an additional sample is drawn to cover persons living in National Health Service/Hospital Trust accomodation.
Sampling Procedure
Source Of Sampling Frame
GB: Royal Mail's Postcode Address File, NI: Rating and Valuation List
Sampling Design
Probability
- systematic
- stratified
- one stage
Primary Sampling Units
Addresses
Secondary Sampling Units
Not used
Stratification Criteria
By frame
Sampling Method
Northern Ireland: single random sampling design +
Far north of Scotland: telephone number is PSU
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
33.10 %
Weighting
Design Weight: Target
Address
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The adjustment procedure is based on a three-stage a posteriori stratification. Figures are based on independent demographic estimates. The stratification variable for the first stage is the Local Authority District or Unitary Authority. This stage makes it possible to make adjustments for different rates of non-response in the various local authority areas and ensures that the results are geographically representative. The second-stage variables are sex and age group. This stratification is intended to ensure that the age profile of the 16-24 year old is correct at national level. The variables in the third stage are region, sex and age group. The three stages are applied by means of an iterative procedure designed to ensure that the estimates are consistent with the stratification variable sets.
IT - Italy
National Reference
Producer
Italian National Institute of Statistics
Universe
The reference population is the population recorded in the registry offices in the Italian municipalities living in private households.
Sampling Procedure
Source Of Sampling Frame
Municipal registers
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Municipality
Secondary Sampling Units
Households
Stratification Criteria
Size categories of municipalities within NUTS3 region
Panel Design
Number Of Rotational Groups
4; 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
34.75 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
Correction factors for the households' non-response are worked out as the reciprocal of the response ratio for each strata.
Coverage Adjustment Weight: Method
The correction factor that assures the sample replies the same structure as the population is determined with regard to the distribution by sex and age groups at NUTS 2 area and by sex and age groups of different width at NUTS 3 area.
PL - Poland
National Reference
Producer
Central Statistical Office of Poland
Universe
All persons 15+ and over with usual residence in Poland.
Sampling Procedure
Source Of Sampling Frame
Census, Register of housing units
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Census enumeration units
Secondary Sampling Units
Dwellings
Stratification Criteria
Region, urban/rural, urbanisation
Panel Design
Number Of Rotational Groups
4; 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
40.83 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The weighted response rates are calculated for sampling units stratified a posteriori by six place-of-residence categories. The initial weights are adjusted by the response rates. The adjusted weights are also final for results concerning households.
Coverage Adjustment Weight: Method
The final step consists in modifying the adjusted weights using the population estimates stratified a posteriori by the urban-rural division, sex and age groups.
PT - Portugal
National Reference
Producer
Statistics Portugal
Universe
Individuals residing in a private dwelling during the reference week.
Sampling Procedure
Source Of Sampling Frame
2001 Census of Population and Housing, BGRI - Geographic Information Referencing Base
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Dwellings
Stratification Criteria
Region (NUTS-3)
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
43.53 %
Weighting
Design Weight: Target
Dwelling
Design Weight: Method
Inverse of selection probability
Coverage Adjustment Weight: Method
The weight is derived as the product of a design weight (which incorporates design information and non-response) and a factor that calibrates the sample to the independent demographic estimates (using a posteriori stratification method by NUTS 2, sex and age groups; NUTS 3 by age groups; and NUTS 3 by sex).
CH - Switzerland
National Reference
Corresponding National Study
SLFS – Swiss Labour Force Survey /
SAKE – Schweizerische Arbeitskräfteerhebung
Producer
Federal Statistical Office FSO
Universe
All persons officially residing in Switzerland for the entire year. Swiss citizens, foreign citizens holding a permanent residence permit or a residence permit valid for at least one year, international civil servants, diplomats and their family members all fall into this category.
Sampling Procedure
Source Of Sampling Frame
Telephone directory, Register of foreigners
Sampling Design
Probability
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Households
Stratification Criteria
Region (std sample) / Region + size of nationality group (sample of foreigners)
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Spring results
Type Of Data Source
Survey
Percentage Of Proxy Interviews
0.72 %
Weighting
Design Weight: Target
Person
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
The sample is stratified a posteriori by region (NUTS 2), marital status, age groups, sex, nationality groups. This procedure is applied iteratively. The expansion factor is a factor to the total population aged 15+.
ES - Spain
National Reference
Corresponding National Study
Economically active population survey
Producer
Spanish Statistical Office
Universe
The population residing in private households for more than one year is covered, including servants; persons living in collective households and persons who are temporarily absent are sampled via relatives living in private households.
Sampling Procedure
Source Of Sampling Frame
Census 2001, updated with Population registers
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Households
Stratification Criteria
Population size of municipality
Sampling Method
Sampling Design: Systematic regarding Primary Sampling Units, Random regarding Secondary Sampling Units
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
57.01 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
Every quarter, population projections by age group and Spanish provinces (NUTS 3) are calculated. Projections by age and region are distributed by stratum in proportion to the population of each stratum. In each stratum, age group and region, the weighting is determined by the ratio of the projection to the sample size.
Coverage Adjustment Weight: Method
The sample is calibrated in order to adjust to the population disribution. The auxiliary information used is the population by sex, age, nationality and NUTS 2. A linear weighting method is used, in which each member of the household has the same weight.
NL - Netherlands
National Reference
Corresponding National Study
Enquête Beroepsbevolking
Producer
Statistics Netherlands
Universe
Persons residing in the Netherlands living in private households.
Sampling Procedure
Source Of Sampling Frame
List of all addresses drawn up by the postal services in combination with the Population Register.
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Municipality
Secondary Sampling Units
Addresses
Stratification Criteria
Region (Corop), employment exchange regions
Panel Design
Number Of Rotational Groups
5
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
46.92 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
A posteriori stratification in two stages is applied, using independent demographic information. A linear weighting method in which each member of the household has the same weight is used. For a posteriori stratification are used: a detailed breakdown by age, sex, ethnic background, martial status and region.
Coverage Adjustment Weight: Method
Weights are benchmarked to the population totals without the institutional population.
EE - Estonia
National Reference
Corresponding National Study
Estonian Labour Force Survey
Producer
Statistics Estonia
Universe
The target population comprises all persons aged 15-74 years with permanent residence in Estonia living in both private and collective households.
Sampling Procedure
Source Of Sampling Frame
2000 Population and Housing Census
Sampling Design
Probability
- systematic
- stratified
- multi-stage
Primary Sampling Units
Households
Secondary Sampling Units
Individuals
Stratification Criteria
Region
Panel Design
Number Of Rotational Groups
4; 2-(2)-2
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
14.87 %
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
For non-response adjustment the non-response correction factors are computed. The homogeneous response groups of reasonably uniform size of sampled households are formed on the basis of the place of residence of the household according to the non-response rate in the region. Within each group the correction factor is inversely proportional to the overall response rate in the region.
Coverage Adjustment Weight: Method
The weights are calibrated so that they produce exact population numbers in certain subgroups known from demographic data (including institutional population). For working-age persons the subgroups by sex, age, place of residence and Estonians/non-Estonians are considered. For this purpose the linear consistent weighting method is applied. For non-working-age persons the non-response adjusted household's weights are calibrated by sex and age.
EL - Greece
National Reference
Producer
Hellenic Statistical Authority (EL.STAT)
Sampling Procedure
Source Of Sampling Frame
Census 2001
Sampling Design
Probability
- random
- stratified
- multi-stage
Primary Sampling Units
Area units
Secondary Sampling Units
Dwellings
Stratification Criteria
Region (NUTS-3)*urbanisation
Panel Design
Number Of Rotational Groups
6
Data Collection
Date of Data Collection
Continuous survey
Type Of Data Source
Survey
Percentage Of Proxy Interviews
44.24%
Weighting
Design Weight: Target
Household
Design Weight: Method
Inverse of selection probability
Non-response Weight: Method
No stratification is carried out a posteriori.