Labour force, monthly figures

Survey characteristics
Purpose

To describe the labour force in the Netherlands per month. The unemployed labour force is the key characteristic.

Target population

Persons of 15 years and older in the Netherlands, excluding persons in homes and institutions.

Statistical unit

Persons.

First year of survey

Monthly figures on the labour force were published for the first time in July 2010. The figures are available from the month under review January 2003.

Frequency

Monthly

Publication strategy

Monthly figures on the labour force broken down by sex and age (15 until 25 years, 25 until 45 years, 45 until 65 years) are available approximately three weeks after the month under review. They are always final and serve as a basis for the quarterly and yearly figures on the labour force that are a mean of  the separate monthly figures.

How is the survey carried out

Survey type

The monthly figures on the labour force are composed based on data from a sample survey, the Dutch Labour Force Survey (LFS).

Survey method

The Dutch LFS is a so-called rotating panel survey with five waves. Respondents are once interviewed  thoroughly by an interviewer of Statistics Netherlands. This takes place by means of a face-to-face interview (Computer Assisted Personal Interviewing, CAPI) or an interview by phone (Computer Assisted Telephone Interviewing, CATI). After that they are contacted by phone every three months for four more times. This survey method was introduced in the last quarter of 1999.

Respondents

Per household a maximum of eight persons aged 15 years or older is interviewed.

Sample size

In 2009 over 64 thousand addresses were put out. This is an average of over 5,3 thousand addresses per month.

Checking and correction methods

The information of the respondent is checked for internal inconsistencies. Through the weighting method over- and underrepresentation of certain groups in the response is corrected. With a structural time series model sample information, including data that was observed in a previous period, is used in an efficient way.

Weighting

The weighting of the observations takes place in two steps. In the first step inclusion weights are assigned to the observations. These inclusion weights are calculated so that they can correct for uneven inclusion probabilities that follow from the applied sampling method. In the second step final weights are determined. With this step the bias caused by non-response is reduced. For this, information on sex, age, country of origin, official place of residence and some other regional classifications are used. Next to this, information from registrations on country of origin, registration at employment office and income is used. For the monthly figures all waves are weighted separately, which makes it possible to compute five separate series for the labour force. These series serve as input for the structural time series model.

Time series model
The size of the unemployed and the employed labour force in a certain month is connected to the size of the unemployed and employed labour force in previous months. Therefore it makes sense to improve the precision of the monthly estimates by using sample information from previous periods.  This information  is also used to determine the monthly seasonal effects. With this the monthly developments in the unemployment can also be judged without seasonal effects. The available information from the five waves is integrated by the time series model into one set of estimations for the labour force by age and sex.

How accurate are the results
Accuracy

The outcomes of the Dutch LFS are subject to a margin of error. Because the sampling design is complex, estimating the 95%-margins of confidence is not easy. Because of the considerable relative inaccuracy figures under a certain threshold are not published. In the tables these figures are replaced by a dot (.).

Sequential comparibility

Monthly figures on the labour force are available from the month under review January 2003. In July 2010 these figures were published for the first time. Before this three-month-averages were used. These figures were available from the period under review December 2000 – February 2001.

Quality strategy

During the interview the answers are put into a computer; with this inconsistent answers can be spotted immediately. With proxy-answering ( when a member of the household answers the questions that concern another member of the household) it is checked whether this person has enough information to answer the questions.