Austria 1987 - 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 BASED ON THE CSP PANEL
| A. GENERAL INFORMATION
back
Official name of the survey/data source:
LIS name:
Administrative unit responsible for the survey:
Funding for the Austrian Microcensus is provided for by the budget of the Austrian Central Statistical office. Copies of the original codebook and other documentation can be obtained from the Department for Social Statistics at the above address. The principle users of the data collected in this survey are the Austrian Central Statistical Office, academic researchers, government departments, etc.. The Austrian Microcensus was set up in 1967. It was conceived as a multi-purpose survey, combining a core-questionnaire with items on labor-force-participation, age, sex, etc., with varying supplementary programs on topics out of the whole field of social statistics. Since 1981, every odd year the monthly income of employees and pensioners has been asked in the Austrian Microcensus. The Austrian Microcensus is the only source on household income in Austria. The process of data collection for the 1987 Austrian Microcensus was begun and completed in September 1987; the information being collected retrospectively for 1987. Use of this data is restricted. Microdata are released only at special request to well-known experts or scientific institutions. They have to be used only for a specified project. Copyright remains at the Austrian Central Statistical Office. No transmission of the copy to a third party. Published results have to remit without costs. A bibliography of the most important publications based on the Austrian
Microcensus is provided in the bibliography in Section M. Also included
in the bibliography in Section M is a list of available user documentation
for the Austrian Microcensus. Also included in section M is a list of available
user documentation for the Austrian Microcensus.
B POPULATION AND SAMPLE SIZE, SAMPLING METHODS back In the period from 1974 - 1993 a one stage stratified systematic random sample design (not self-weighting) is employed in the Austrian Microcensus. The Austrian Microcensus primarily addresses the universe of all persons residing in Austria. As persons are determined by way of selecting dwellings it is possible, in addition, to analyze the universe of (private) households and dwellings. All persons and households living in a selected dwelling belong to the sample and have to be interviewed. With regard to persons the sample is therefore clustered. Such a selection misses all persons (and their households) which do not live in dwellings but in institutions, shelters, refugee camps, etc.. Therefore, the Austrian Microcensus sample of dwellings is supplemented by a sample of persons living in institutions with more than fifty inhabitants, which is carried out once a year (March) by postal inquiry - the core questionnaire not the supplementary program. For the selection of the sample for the years 1984 - 1993 extensive use was made of data and materials available from the 1981 Census of Population and Housing. Strictly speaking the frame of selection consists of three parts whose combination results in the final frame. These three parts are the stock of dwellings in 1981 (last Population and Housing Census); new-built dwellings from 1981 on (from current building statistics) and the institutional population. As the main sample frame of the Austrian Microcensus was based on material from the Census of Population and Housing it was possible to stratify the dwellings according to their characteristics and those of their inhabitants. The sample size amounts to 29,000 dwellings (out of a population of
2.9 million) which are distributed among the nine federal states so as
to result in an equal number of persons selected per state. 4,300 dwellings
were allocated to Vienna capital, and between 2,000 and 3,400 dwellings
to each of the other 8 federal states. In smaller states the probability
of selection of a dwelling is higher than in bigger ones. 23,000 households
were actually surveyed. (3,000 - 6,000 (housing unit) sample units in the
sampling frame were not interviewed). This was the same sample that was
made available to LIS.
C. MEASURES OF DATA QUALITY back About 23,000 households were actually surveyed. Out of the sample some households could not be interviewed because of illness of the interviewer, untraceable address or other reasons. Some dwellings are found to be non-existent at the time of the interview (demolished), no longer used as permanent living quarters or vacant. Among the remaining units assigned for interview there are dwellings where inhabitants were not available for interview (e.g. seasonal workers, especially in construction and tourism). The response rate for the core questionnaire is about 80%. The 6,000 dwellings where an interview could not take place are divided into two groups: one half of refusers and households which where not met by the interviewer, the other half of dwellings was found to be non-existent at the time of the interviewer or could not be interviewed because of illness of the interviewer. Because the Austrian Microcensus has a rotating sample design, some information about non-responding households that responded in the previous surveys are available. The link between compulsory and the voluntary parts of the questionnaire
certainly helped to keep down non-response in supplementary programs (normally
an additional 5 to 15%). The non- response rate is generally low for programs
addressing households (only one person out of the household has to provide
the answer); the response rate in programs addressing the unit "person"
depends on the content of the program. Refusals are especially high of
questions related with income (nearly 30%). Because of the lack of knowledge
of the German language, immigrants (especially unskilled workers) were
often not able to answer all questions.
D. DATA COLLECTION AND ACQUISITION back Data collection is almost exclusively done by face-to-face interviews, with the use of optical readable forms. About five percent of the interviews are telephone interviews. There was an opportunity not to tell the amount of the income to the interviewer, but to note it at a special sheet and to mail it or to give it sealed to the interviewer (about 2% of the income data). The recruiting and most of the training of the interviewer staff (about 1,350) is done by the statistical offices of the federal provinces which don't belong to the ACSO. For topics of the supplementary programs, the interviewers did only get written manuals worked out by the ACSO. Supervision was done by both provinces and the ACSO. Each resident in the selected housing unit had to be interviewed. For
each person there was a separate sheet. The questionnaire consists of a
core questionnaire and a supplementary program. In September 1987 the special
program consisted of questions related to working hours and to income.
Participation to the core questionnaire was required by law, participation
in the supplementary programs was voluntary. Answers could be given by
some other household member. Respondents were not asked to consult or use
pay records, tax returns, etc. The income questions were not asked to the
self-employed.
E. WEIGHTING PROCEDURES back The basic weight is the reciprocal of the sampling fraction. It is adjusted for general non-interview and non-response, but not for non-response of the special program (e.g. income questions). The weighting did not help adjust for missing data or other non- sampling errors related to income. The sum of the survey weights are equal to the total number of units in the sampling frame. For the 1989 and the 1991 income survey a 'hot-deck' procedure was implemented
to cover the missing income values for all persons except the self-employed;
the income tables published by the ACSO had not yet such a 'hot-deck' procedure
but users could implement their own method if necessary. Information on
the Hot-Deck used by the ACSO can be obtained by Walter Wolf.
F. DETERMINATION OF SURVEY UNIT MEMBERSHIP back The basic units of aggregation of the Austrian Microcensus are persons
and households. Children away from home or attending school or other educational
institutions, husbands away from home at work or on military duty are included
as household members. Students are partly counted at their parents and
at the place of studies. There were also some difficulties to cover young
working adults. The head of the household was designated by the household
itself.
G. CHILDREN AND SPOUSES back For income the definition of 'children' is derived from age and from economic dependence (operationalized with the right to receive a family allowance). Children are pre-school-children, students, children at school, apprentices or other supported persons who should not be older than 27 years. In the regular tabulations of Microcensus statistics unmarried persons with no children within the household and living with at least one parent or grand-parent in the household are considered to be children. The Microcensus provides information to distinguish between children of the unit head (or spouse) and children of some other household member or someone living outside the household. Other definitions e.g. for age limits are possible. In the general tabulations of the Microcensus the spouse is defined
as the person married to or living in consensual union with the head of
household.
H. AVAILABILITY OF BASIC SOCIAL AND DEMOGRAPHIC INFORMATION back In Table 1 are summarized the basic social and demographic information. Table 1
I. AVAILABILITY OF LABOUR MARKET INFORMATION back Labor force status information is available for this survey. No groups were excluded at the time of interview through filter questions relating to the employment status of the respondent, although only income recipients were requested to provide answers to the income schedule. The labor market information which is available in the survey is summarized in Table 7.3. Table 2:
J. AVAILABILITY OF GEOGRAPHIC INFORMATION back The geographic location is based on the residence of the respondent
household (across of the dwelling). The smallest units for publication
of income data are federal provinces and urban rural dimensions (stratified
by population number and share of agricultural population).
K. SOURCES AND AMOUNTS OF CASH INCOME back Only net earnings for employees, net pensions for pensioners and unemployment benefits for unemployed persons are available. Incomes from self-employment and property are not available for the reason of political sensitivity by the respondent. The received amount of family allowance is known. Following the importance of seasonal unemployment in Austria, these impacts have to be introduced in the calculation of the annual income. To record the sources and amounts of income received a reference period
of one year was used.
L. TAXES back Taxation information is not available for this survey. According to the
low taxation of the 'special bonuses' received by almost all Austrian employees
(approximately 1/7 of the annual gross income) adaptations for the annual
net income are necessary.
M. BIBLIOGRAPHY OF MAIN PUBLICATIONS BASED ON THE CSP PANEL back "Personen- und Haushalteinkommen von unselbständig Beschäftigten", Beiträge zur österr. Statistik, Heft 924. "Arbeitszeit", Beiträge zur österr. Statistik, Heft 974. "Personen-und Haushaltseinkommen der unselbstandig Beschaftigten", Statistische Nachrichten, 10/1992. "Arbeitszeit 1991: Regelarbeitszeit, Uberstunden, Wochenend-, Nacht- und Schichtarbeit., Statistische Nachrichten, 11/1992. "Regionalergebnisse zur Einkommensverteilung der Unselbstandigen", Statistische Nachrichten, 12/1992. |