Switzerland 1982 - documentation

Table of Contents

• A. GENERAL INFORMATION
• B. POPULATION AND SAMPLE SIZE, SAMPLING METHODS
• C. MEASURES OF DATA QUALITY
• D. DATA COLLECTION AND ACQUISITION
• E. WEIGHTING PROCEDURES
• F. DETERMINATION OF SURVEY UNIT MEMBERSHIP
• G. CHILDREN AND SPOUSES
• H. AVAILABILITY OF BASIC SOCIAL AND DEMOGRAPHIC INFORMATION
• I. AVAILABILITY OF LABOUR MARKET INFORMATION
• J. AVAILABILITY OF GEOGRAPHIC INFORMATION
• K. SOURCES AND AMOUNTS OF CASH INCOME
• L. TAXES
• M. BIBLIOGRAPHY OF MAIN PUBLICATIONS

 

 

 Official name of the survey/data source:
 Schweizerische Einkommens und Verm"gensstichprobe (Swiss Income and Wealth Survey)

 Administrative unit responsible for survey:
 Volkswirtschaftliches Institut

Funding for the Swiss Income and Wealth Survey was provided for by the Schweizerischer Nationalfonds (Swiss Science Foundation). For additional information to that provided here concerning the sample design, data collection process, demographic information, income information and editing and survey processing, the following address can be contacted:

The Swiss Income and Wealth Survey has been conducted only once--in 1982--and was first made available as microdata in 1984. The main purpose of the survey was to measure income distribution in Switzerland. A similar survey is being conducted for 1992 income.

The process of data collection (i.e. field work) for the first wave of LIS data was begun in 1982 and completed in 1982.

The public has access to the data under the condition that they be used for research purposes only. The Swiss Income and Wealth survey microdata have been made available to the Luxembourg Income Study Project providing a copy of all publications using the Swiss data be forwarded to the Swiss Statistical Office at the address above.

A bibliography of the most important publications based on the Swiss Income and Wealth survey data is provided in Section M. Also included in the bibliography is a list of the user documentation for the Swiss Income and Wealth survey data.

B. POPULATION AND SAMPLE SIZE, SAMPLING METHODS back   

 For this survey all the data were taken from administrative tax records. No interviews were conducted.

Two final stage sampling frames were used in the Swiss Income and Wealth Survey. The main sampling frame consists of a list of registered voters (i.e. Swiss citizens) which was compiled from separate lists kept by the communal administrations. An additional sample of foreign nationals holding permanent residence was randomly selected from a central register of foreign nationals kept by the Swiss government (Zentrale Ausl„nderregeister).

Foreign household heads without permanent residence permits were not included in the sampling frame. Military personnel, and people living in institutions or other group situations were included in the sampling frame. Once the sample was selected from the sampling frame, all sampling units were included in the survey, except for mentally disabled persons who were excluded.

 1. The Sample Design

 The Swiss Income and Wealth Survey utilized a stratified sample design, which was constructed as follows: 

1. Each linguistic region (German, Italian and French) was stratified by size of village (small and large).
2. In the large villages addresses were selected using a simple random sampling procedure. The sample size was proportional to the number of citizens in a village.
3. In the small villages in each linguistic region a clustered sample was selected.

Foreigners, and individuals residing in the Italian and French speaking regions of Switzerland had higher selection probabilities than people living in the German speaking area. Weights have been calculated to adjust for this.

Tax units were the primary collection unit. (See Section G below, "Children and Spouses," for information on the definition of a "tax unit.")

All households containing married couples had a sample selection probability twice that of non-married individuals. This is because both a wife's and husband's names are included in the voter registration list or the register of foreign nationals. (However, tax units consisting of married couples have been weighted by a factor of 0.5.) Children under 20 years of age are considered members of the tax unit, but these individuals were ineligible to vote, and hence were not on the sampling frame lists. Consequently, their inclusion does not affect a tax unit's sample selection probability, and no weights are required to adjust for them.

Weights have also been calculated to take into account sex and age, which afected sample selection probabilities.

There were a total of 7,036 tax units for which data was collected. 6,055 of these were comprised of Swiss citizens, and 981 by foreigners. The sample that was made available for the LIS database was comprised of 7,036 cases, of which LIS was able to make available to its users all 7,036 cases.

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

 For 128 (1.8%) of the 7,036 cases income data is not available. All the information collected in this survey came from administrative tax records, and these 128 cases are those people who still had outstanding extensions granted, at the time of data collection, for their reporting of income tax. None of these households contained Swiss citizens. These cases have been weighted by a factor of 0.

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 national tax data. Internal edits, and checks for consistency errors have been performed.

3. Data Corrections and Adjustments

 Apart from the internal edits and consistency checks mentioned above, no other corrections to the original survey data have been made.

4. General Assessment of Income Data Quality

Users of The Swiss Income and Wealth Survey should be aware of the following problems regarding the quality of the income data collected in this survey: 

1. Missing values are coded as 0;
2. No income information exists for household members other than the household head and spouse;
3. Not all categories of foreigners are included in the survey (e.g. guest workers are excluded);
4. Households are defined in terms of tax units.

D. DATA COLLECTION AND ACQUISITION back 

1. Method of Data Collection

The data were collected from tax file documents held by the communal administrations. Taxation employees collected the required information from tax files. (See Section B.)

 2. Structure of the Survey Instrument

 Tax documents were used to obtain the data. The income and asset variables were collected for 1978, 1980 and 1982; the socio-demographic variables for 1980 and 1982.

3. Survey Respondent Rules

Because the data collection was carried out by tax administration employees, there were no survey respondent rules. It should be noted that all Swiss citizens and individuals holding permanent residence, who are over 20 years of age, are required to submit an income tax form, even if they have received zero income.

E. WEIGHTING PROCEDURES back 

For the Swiss Income and Wealth Survey weights have been assigned to each sample case. These weights were assigned in order to adjust for differential sampling probabilities which were built into the sample design. The Italian linguistic region (Tessin), foreigners, and women were oversampled. An additional weighting procedure was developed by the survey administrators to adjust for the proportion of married couples in the survey.

Because women were granted the right to vote only in 1972 in Switzerland there were some problems with the number of women who were registered voters. These sampling probability differences between males and females were taken into account in the calculation of weights.

The sum of the survey weights is equal to the total number of units in the sampling frame.

F. DETERMINATION OF SURVEY UNIT MEMBERSHIP back 

 The basic unit of aggregation which was used in this survey was the tax unit. This could, for example, be a single individual with no spouse or dependents, or a husband and his spouse and those supported by either the husband or wife. In order to determine whether or not a person is considered a member of the survey unit (for example, children, students away from home and attending a school or other educational institution, husbands away from home at work, or elderly family members living in a nursing home) they had to be supported members of the tax unit.

The overall sampling unit cannot be divided into subgroups in those situations where several families share the same housing unit.

G. CHILDREN AND SPOUSES back 

Children were registered in the Swiss Income and Health Survey, but no further information is available about them. This includes characteristics such as their sex and age. Neither does the survey provide 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 the case of married couples, the man is always considered the head of house, and his wife as "spouse." Some types of family or household arrangements are classified as comprising of two or more tax units. For example, two individuals who are living together as a non-married couple are required to fill out two separate income tax forms, and neither tax form would make any reference to the other cohabiting partner. Consequently, they would be considered two separate tax units. The rule is that if someone is not considered a spouse or a dependent for taxation purposes they are not in the househiold tax unit.

Married couples with children of 20 years or more who are dependents (e.g. students) are considered a single tax unit. However, because dependent children are required to fill out a tax form, the child, if selected in the sample, would appear as a separate household. (On the other hand, if the mother or father is selected, the dependent child is considered such and appears as a member of the parents' household.) Note that there are individuals, over 20 years of age, classified as separate tax units, with zero income, who appear in this survey. Many of these people are actually dependent children living at home with their parents! They are not individuals living alone. It is not possible to identify them with certainty. You may wish to delete single person households with zero income, over age 20 (and perhaps under 30, although this latter figure is an arbitrary number) from your analyses.

Divorced individuals, single parent families, and female headed households are identifiable.

Other than children and spouses, it is also possible to identify grandparents and other relatives.

H. AVAILABILITY OF BASIC SOCIAL AND DEMOGRAPHIC INFORMATION back 

In Table CH82.1 are summarized the basic social and demographic information which is available in the Swiss Income and Wealth Survey.

Table CH82.1
Basic Social and Demographic Information

I. AVAILABILITY OF LABOR MARKET INFORMATION back 

Labor force status information is available in this survey for all Swiss workers, but not for guest workers who were not included in the survey.

The available labor market information is summarized in Table CH82.2.

Table CH82.:
Labor Market Information

J. AVAILABILITY OF GEOGRAPHIC INFORMATION back 

It is possible to identify the geographic location of the sampling units in this survey. The geographic categories which are used in this survey are size of village, type of area, and linguistic region.

K. SOURCES AND AMOUNTS OF CASH INCOME back 

 Sources and amounts of income are recorded for an annual period, the year being 1982. The amounts recorded were the actual amounts received. Income sources and amounts are not recorded for each person.

L. TAXES back 

Taxation information is obviously available, given that the Swiss Income and Wealth Survey data were obtained from administrative taxation records.

M. BIBLIOGRAPHY OF IMPORTANT PUBLICATIONS back 

Buhmann, Brigitte; 1988: Wohlstand und Armut in der Schweiz, Eine empirische Analyse für 1982, Basler Dissertation, Grsch.

Leu, R.E.; R. L. Frey; (1985a): "Distributional Impacts of Government Policies in Switzerland".
In: Environment and Planing: C: Government and Policy. Vol. 3, 199-213.

 Leu, R.E.; R.L. Frey; (1985b): "Budget Incidence, Demographic Change and Health Policy in Switzerland". In: Terny, G. Culyer, A.J. (eds) (1985): Public Finance and Social Policy, Detroit.

 Leu, R.E.; R.L. Frey; B. Buhmann (1985c): Taxes, Expenditures and Income Distribution in Switzerland". In: Journal of Social Policy, Vol. 14:3, 341-360.

 Leu, R. E.; B., Buhmann; R. L. Frey (1986): "Die personelle Einkommens- und Verm"gensverteilung in der Schweiz 1982". In: Schweizerische Zeitschrift für Volkswirtschaft und Statistik. Vol. 169:2, 111-142

 Leu, R. E.; B. Buhmann ; R.L. Frey, (1988a): "Die personelle Einkommens- und Verm"gensverteilung in der Schweiz 1982". In: Frey, R.L. ; R. E. Leu; (1988): Wohlstandsverteilung und -umverteilung in der Schweiz. Basel.

 Leu, R. E.; B. Buhmann; R.L. Frey, (1988b): Steuern, Transfers und Einkommensverteilung in der Schweiz 1982". In: Frey, R.L.; R. E. Leu; (1988): Wohlstandsverteilung und -umverteilung in der Schweiz. Basel.

 Gutzwiller, F.; R. E. Leu; H.-R. Schulz; 1985: "Eine schweizerische Gesundheitsbefragung (SOMIPOPS). Methoden zur Definition und Erfassung von Gesundheits- und Versorgungsindikatoren". Teilprojekt des Schweizerischen Nationalfonds Nr. 4.350.0.79.08 Arbeitsbericht, Basel.