|
?:comment
|
-
Note:
There are two subsamples in the data for the United Kingdom, one for Great Britain and one for Northern Ireland. The two subsamples are completely independent of each other. Among other things, the institutes conducting the survey differ, as do the survey dates and periods. In addition, the provided subsample for Northern Ireland contains more cases than the subsample for Great Britain and there is no weighting factor at hand that brings the two subsamples into a proportion appropriate to the population, as the weighting factors available for the two samples serve to compensate for unequal selection probabilites introduced by sampling design or non-response within the respective subsample only. If the United Kingdom is taken as one unit of analysis, all these factors should be taken into account.
(en)
-
Weighting factor
For detailed information and explanation about the construction of the total weight see 'Study Description' or 'Background Variables' documentations for each country.
AR: The weights for each stratum were defined as the product of two ratios. The first is the quotient of the population 18+ of each stratum divided by the total population 18+; the second is the quotient of the total effective sample size divided by the effective sample size of each stratum.
CA: Weight calculated on age; design weight to adjust for unequal selection probabilities stratified by province.
CH: The design weight is defined according to three probabilities of selection: 1. Probability for the localities to be selected in the country, 2. Probability for the sample points to be selected in the localities, 3. Probability for the respondents to be selected in the household.
CL: The sample was weighted in order to adjust for non-response bias. Variables used for calculation of weight are gender and age.
CZ: Total weight is constructed from: 1. design weights based on proportion of household sizes, 2.
Post-stratification weights based on region, sex, education, age, economic activity, and size of the community. The weights were derived from data of the Czech Statistical Office. Method: ranking based on loglinear modelling.
DE: Respondents living in the eastern part of German are oversampled. If all of Germany is taken as the unit of analysis (rather than eastern and western states), the design weight provided in this variable must be used. The weighting factors were calculated based on data of Microcensus 2005 provided by the German Federal Statistical Office.
FI: Weight_2 included in the dataset: does not have the expansion property (the mean of the weights is 1 and the sum of the weights is the number of accepted responses, i.e. the size of the data).
FR: Post-stratification weight computed on sex, age and occupation
GB-GBN: Weight to adjust for non-response bias. A number of area level and interviewer observation variables were used to model response.
GB-NIR: It is not possible, using the Postcode Address File, to select addresses with probability proportionate to the size of the household. To compensate for this potential source of bias, the data should be weighted before analysis. The weighting adjusts for the fact that individuals living in larger households had a lower chance of being included in the sample than individuals living in smaller households. The data are weighted in relation to the number of eligible adults at that address, derived from the details of the household structure recorded by the interviewers. In order to retain the actual number of interviews, the weighted sample was scaled back to the originally obtained sample size.
NL: weight adjusts for household size, differences from sample frame with respect to location, for difference due to within household replacement - with respect to age, sex, position in household, education, main activity and adjusts for non-voting.
PL: Variables used for calculation of weight are region, size of place, sex, age (categories) and education.
PT: The sample was weighted in order to correct the bias of the data regarding the distribution of the population in the following variables: sex, age and level of education.
SK: Redressment weight, adjusts for sex, age group, education, nationality, size of community, and region.
TW: Design weight to adjust for unequal selection probabilities.
US: The US weight takes into consideration the sub-sampling of non-respondents, and the number of adults in the household. It also essentially maintains the original sample size.
ZA: Person and household weights are benchmarked using the SAS CALMAR macro and province, population group, gender and 5 age groups as benchmark variables for persons and province and population group of the respondent in the household for households as benchmark variables. The marginal totals for the benchmark variables are obtained from the applicable midyear estimates as published by Statistics South Africa. In other words, the estimated South African population for the applicable year is used as target population.
(en)
|
|
?:groupDescription
|
-
Das International Social Survey Programme (ISSP) ist ein internationales Kooperationsprogramm, das jährlich eine Umfrage zu sozialwissenschaftlich relevanten Themen durchführt. Seit 1985 stellt das ISSP internationale Datensätze bereit, die internationale und kulturübergreifende sozialwissenschaftliche Forschung über Zeit ermöglichen.
(de)
-
Die ISSP-Module "Role of Government" befassen sich hauptsächlich mit Themen wie der Einstellung zu staatlichen Aufgaben und Ausgaben, staatlichen Eingriffen in die Wirtschaft, bürgerlichen Freiheiten, politischen Interessen, Vertrauen und Effizienz.
(de)
-
ISSP Role of Government modules mainly deal with issues, such as attitudes towards government responsibilities and government spending, state intervention in the economy, civil liberties, political interest, trust and efficacy.
(en)
-
The International Social Survey Programme (ISSP) is a continuing annual program of cross-national survey collaboration, covering a wide range of topics important for social science research. Since 1985 the ISSP provides international data sets, enabling cross-cultural and cross-temporal research.
(en)
|
![[This page as RDF]](https://data.gesis.org/gesiskg/static/rdf-icon.gif){kind=icon}