Labour force survey 2018
LFS 2018
LFS 2018
Traitement statistique
Frequency of data collection
Continuous
Data collection
The survey is conducted continuously, every week of the year.
Data is collected by computer-assisted data collection (CAPI). The interview is done
face to face for the first and last waves and by phone for the intermediate waves.
If a person cannot respond (or does not want to), another person household can answer
in their place (proxy).
An annual specific survey is conducted in Mayotte.
Data collection period
The data collection is conducted continuously, every week of the year. The interview
is usually conducted in the 2 weeks and 2 days following the reference week.
Each dwelling is surveyed six consecutive quarters.
Collection mode
- Face to face by interviewer
- By phone
Survey unit
Household
Sampling method
The sampling frame is the housing-tax register for Metropolitan France and the annual
census survey for DOM.
In Metropolitan, the sampling design consists in a selection of sectors divided in
6 adjacent clusters; a cluster being a set of nearby dwellings of about 20 main residences.
The sample is rotational: each cluster is surveyed 6 consecutive quarters, then replaced
by a new cluster of the same sector.
The same sample design (cluster / rotational) is used for DOM.
For Metropolitan France, the sample is stratified by region. For each region, the sample is balanced, proportionnaly of the number of main residence, on some variables from the sample frame.
For DOM, the sampling is stratified (geographic strata) and systematic (with equal inclusion probabilities, within geographic strata).
The sample is uniformely distributed among the 13 weeks of the quarter. Each cluster is affected to a reference week.
The sample rate is 1/400.
The complementary module is asked to the outgoing clusters.
Sample size
Each quarter, 92,000 dwellings are surveyed, 73,000 of which are principal residences and are in the target population.
Data collection documents
Ad-hoc module LFS 2018
Data compilation
For Metropolitan France, a unique calibration is performed both to correct biases
induced by non-response and to get consistency with external margins. The margins
are individual characteristics (sex, age, NUTS2,...) and dwelling characteristics
(number of dwellings, type of housing, income of the households,...).
For DOM, weights are first adjusted by using an estimation of response probabilities,
and are next calibrated on external margins (number of dwellings, type of housing,
diploma, place of birth...).