Official name of the survey/data source:
Panel Socio-Economique "Liewen zu Letzeburg" (PSELL)
(The Luxembourg Household Panel Study)

Administrative unit responsible for the survey:

CEPS/INSTEAD is a research based institution established by the state of Luxembourg. Funding for the survey is provided for by the government of the Grand Duchy of Luxembourg.

The data are stored at CEPS/INSTEAD at the address above. Copies of the original codebook and other documentation can also be obtained from CEPS/INSTEAD.

The following people, all at the above address, can be contacted for more information about various aspects of the survey: Pierre Hausman, Bernard Gailly (Sampling and Sample Selection); Andree Kerger, Günther Schmaus, Jean-Jacques Wester (Data Collection Process); Pierre Hausman, Bernard Gailly, René Denver (Demographic Variables); Pierre Hausman, René Dewever (Income Variables); Günther Schmaus, Jean-Jacques Wester, René Dewever (Editing/Survey Processing).

The principle users of the data collected in this survey are the European Statistical Office (EUROSTAT), the University of Nancy (ADEPS), the Panel Socio-Economique "Liewen zu Letzeburg" team, and the Luxembourg government.

The Panel Socio-Economique "Liewen zu Letzeburg" (PSELL) is conducted every year. The first year in which the PSELL was conducted was 1985, and was first made available as microdata in 1985.

The main purpose of the survey is to measure unemployment, poverty, labor force participation, income and family expenditure.

The process of data collection for the PSELL was begun in April 1985 and completed in April 1985.

There are no restrictions on the use of this data by the public.

A bibliography of the most important publications based on the PSELL 85 data is provided in Section N. Also included in the bibliography in Section N is a list of user documentation for the PSELL data.

B POPULATION AND SAMPLE SIZE, SAMPLING METHODS back

The sampling frame for the PSELL survey consists of registers of the social security system held by L'inspection Générale de la Securité Sociale (IGSS), supplemented by other sources (Centre Commun d'Affiliation). This combined sample frame covers 97% of the resident population of Luxembourg. Household heads who are of foreign nationality, and some people with very low and very high incomes who were not attached to Luxembourg social security system were not included in the sampling frame. These represent 3% of the resident population.

People living in institutions such as prisons, homes for the elderly, or other group situations were not included in the survey. Military personnel were not included in the sampling frame. Once the sample was selected from the sampling frame, all sampling units were eligible for interview.

1. The Sample Design

The PSELL was based on a random probability sample selected from social security lists. The sampling unit is the "titulaire principal". A total of 168,234 individuals were registered on the social security list at the time the sample was selected.

The total number of respondents who were actually surveyed in the PSELL was 6,110 (individual level), and 2,012 (household level). When weighted this amounts to 4,354 cases (individual level), and 1,585 (household level). The same sample size was made available for the LIS database. LIS was able to make available to its users all cases.

There were 1,278 sample units which were not interviewed because they refused, had moved, were deceased, or were institutionalized.

Tests have been performed to detect non-response bias. The results of these tests suggest bias from non-response is negligible.

All geographic areas in the country were included in the sample design.

Estimates of sampling variability (standard errors) have not been computed for this survey.

C. MEASURES OF DATA QUALITY back

1. Item and Group Nonresponse Rates

The overall non-response rate to the survey was 27.3%, which represents a total of 1,278 cases. An evaluation of non- response by area and sex was performed.

2. Reporting and Under-Reporting and Income Data Quality

An evaluation of the quality of the income data has been made by comparing the survey data with other surveys. More detailed information can be found in PSELL: Sample Design, No. 14.

An evaluation of the quality of demographic data, and the estimation of some budgets (Social minimum income: R.M.G) has been made. (See PSELL: Sample Design, No. 14)

Internal edits, or checks for consistency errors or for data items have been performed. Because the PSELL is a panel survey, it was possible to check the longitudinal consistancy of the responses.

3. Data Corrections and Adjustments

Adjustments to the original data were made in order to improve the data quality. Missing income values were imputed using a deterministic longitudinal method. (See PSELL: Imputation Income, No.27.) Taxation and salary values were simulated.

4. General Assessment of Income Data Quality

Users of this data should be aware of the following problems regarding the quality of the income data collected in this survey. For the self-employed and farmers it is not possible to use external information.

D. DATA COLLECTION AND ACQUISITION back

1. Method of Data Collection

The data was collected via a personal visit by an interviewer. Participation in the survey was was voluntary and privacy was assured. Respondent names were known only by interviewers and two PSELL members involved in the sample selection process. Personal information, such as date of birth and area code, are not accessible to users of the data.

2. Structure of the Survey Instrument

Three questionnaires were used in the PSELL: A household schedule, an income schedule, and a schedule for each individual.

3. Survey Respondent Rules

The head of household or the spouse could provide answers for other household members. The same was true for the income group head and for individuals. Information on who had answered each questionnaire was later checked and encoded.

Respondents were not asked to consult or use pay records, tax returns, or other documents. However, some people did so but it is not known how many.

E. WEIGHTING PROCEDURES back

In the PSELL survey weights have been assigned to each sample case. These weights were assigned in order to adjust for selection bias. These weighting procedures did not help adjust for missing data or other nonsampling errors related to the income data; they were used only to correct for differential selection probabilities.

The PSELL 85 data contains the inverse of the number of official transfer payment recipients present in the housholds.

Estimates derived from the sample are representative of the total population as defined by the sampling frame.

F. DETERMINATION OF SURVEY UNIT MEMBERSHIP back  

The basic unit of aggregation which was used in this survey was the household. Information from individual and group files have been aggregated at the household level.

Households were defined as a housing unit comprised of persons living together, and sharing a common living space such as a kitchen.

In the original file the overall sampling unit can be divided into subgroups in those situations where several families share the same housing unit. The survey unit head was the male in the case of couples, or the owner of the housing unit.

Individuals other than the sampling unit head can be identified are in the original data file of the PSELL. The following relationships of individuals to families within the household can be identified:

1. The relationship of each member to the head of household is encoded.
2. The relationship each household to others in the household (such as partner, father, mother, child, etc.).

G. CHILDREN AND SPOUSES back 

In this survey children are defined as all persons under 16 years and not married. Persons over 16 years, not married, and in training (school or college) are also considered children. However, their education must not have been interrupted for more than 1 year.

The PSELL survey provides information to distinguish between children of the unit head (or spouse), and children of some other household member, or of someone living outside the household.

In this survey the definition of spouses includes persons who are legally married, and cohabiting partners of the head.

H. AVAILABILITY OF BASIC SOCIAL AND DEMOGRAPHIC INFORMATION back

In Table 8.1 are summarized the basic social and demographic information which is available in the PSELL.

Table 8.1
Availability of Basic Social And Demographic Information

I. AVAILABILITY OF LABOUR MARKET INFORMATION back 

Labor force participation was measured as of the time of interview, and since last month. This and other labor market information is summarized in Table 8.2.

Table 8.2
Availability of Labor Market Information

* B.I.T. codes. See Treiman, 1977, Occupational Prestige in Comparative Perspective. New York: Academic Press.

J. AVAILABILITY OF GEOGRAPHIC INFORMATION back

It is possible to identify the geographic location of the sampling units in the PSELL survey. The geographic category which is used in this survey is area code. These are postal codes which can be transformed into canton or commune codes.

K. SOURCES AND AMOUNTS OF CASH INCOME  back

Sources and amounts of income are recorded for a weekly, monthly, and annual period. The amounts recorded were the actual last amounts received. Income sources and amounts are recorded for each person.

L. TAXES back

Taxation information is available for the PSELL. Direct taxes have been estimated for salary incomes.

M. BIBLIOGRAPHY OF MAIN PUBLICATIONS back

Dickes, P.; P. Hausman ; A. Kerger; 1987: Méthodologie générale & répertoire des variables -1985- première vague, PSELL no. 1.

Hausman, P.; F. Courtois; 1987: L'état de la pauvreté au Grand-Duché de Luxembourg, PSELL no 2.

Hausman, P.; 1987: Description des niveaux de vie et de bien-être économique en 1985: principaux résultats,PSELL no.3

Tournois, J.; 1988: Logistique et documentation, PSELL no.9

Tournois, J.; 1988: Documentation transversale des variables "1985": Première vague, PSELL no. 10.

Kerger, A.; R. De Wever; 1988: Description statistique des variables du questionnaire. -1986- Second vague, PSELL no. 12.

Hausman, P; 1990: Le mode d'echantillonage du panel "Liewen zu Letzeburg", PSELL no. 14.

Kerger, A.; 1989: La collecte des données en 1986. Elaboration du questionnaire déroulement de l'enquête, opérations de chiffrement, PSELL no. 16.

Gailly, B.; Hausman, P. ; 1990: Dispositif des pondérations individuelles et des pondérations ménages en 1985 et 1986. -Première version, mars 1990, PSELL no. 19.

Hausman, P.; 1990: Les indicateurs sociaux de pauvreté: Tableaux de base et documentation. PSELL no. 21.

Hausman, P.; 1990: Imputation in income, PSELL no. 27.