|
?:comment
|
-
Weighting factor
No total weight usable for international comparison.
NATIONAL weighting procedures/ variables used for calculation of NATIONAL weights:
AR IS SE SI TR: No weighting.
AT: Weighting variable calculated by the fieldwork/research institute. Weigthing factors: Bundesland (province/region), Sex * Age, Education
AU: Design weight and redressment weight to adjust for non-response bias; variables used for calculating redressment weight: age, sex, highest level of schooling. Weights are rescaled to net sample size.
BE-FLA: The ISSP-questionnaire is an addition to a general face-to-face survey. In a first step weights were computed for this face-to-face survey. Those weights are a combination of design weights, non-response weights and post stratification weights. The design weights compensate for the oversampling of Brussels and some other rural areas.
Non-response weights are then applied to account for unequal probability of response in different subgroups in the population. Age, sex, marital status, type of dwelling, nationality and a geographical classification were used to identify these subgroups. (All these characteristics were known for all sampled units.)
The non-response weights were then adjusted so that respondent sample matched the population in terms of sex and education (population classification based on Labor Force Survey 2009).
In a second step these weights were adjusted to compensate for the non-response to the ISSP-part of the survey. We used the following variables of the general survey for this non-response weighting: age, sex, level of education, nationality, professional status, attitude towards surveys and an assessment by the interviewer of the respondent’s aversion towards answering survey questions.
Finally the weights were scaled to make the weighted sample size equal to the unequal sample size.
BG: Weighting variable has been computed and accounts for sex, settlement and age-groups. There are twenty coefficients - 4 groups (male and female for towns and villages) multiplied by five age groups (18-24 years, 25-34 years, 35-44 years, 45-54 years, 55-64 years, 65-84 years, 85 years and over).
CL: Weight to adjust for non-response bias on gender, age and urbanity.
CZ: WEIGHT include total weight, which was constructed from design and post-stratification weights. Design weights based on proportion of household sizes. Post-stratification weight based on region, community size, sex, age and education. The weights were derived from data of the Czech Statistical Office.
DE: Two separate German samples: the sample for eastern Germany deliberately over-samples the five eastern federal states. If all of Germany is taken as the unit of analysis (rather than the eastern and western states), design weight is necessary: weighting factor for Western Germany: 1,16307166*; weighting factor for Eastern Germany: 0,61416777*; The two weighting factors are stored in the weight variable.
ES: Weights have been calculated using two variables: Autonomous Communities (ES_REG), and Size of Municipalities (ES_SIZE).
FI: Weight used for calculation by calibration method considering gender, age classes, NUTS3 regions with Greater Helsinki as separate region and type of community. Weight doesn't 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 weighting computed on sex, age (4 groups: 18 to 29 years old, 30 to 39 years old, 40 to 54 years old, 55 years old or more) and occupation (6 groups : Farmers, Tradesmen, Shopkeepers and Business Owners; Managers and Secondary/University Teachers, Intermediate Professions, White Collar Workers, Blue Collar Workers, Unemployed)
GB-GBN: Weights needed to be applied to correct for unequal probability to be selected (one person interviewed at each address independently from household size). Non-response weighting then applied to correct for unequal probability of response in different sub-groups in population.The final stage of weighting was to adjust the final non-response weight so that the weighted respondent sample matched the population in terms of age, sex and region. Very large weights were capped and were scaled to make the weighted sample size equal to the unweighted sample size.
LT: Weight based on age and gender.
MX: Weight to adjust for non-response bias on the variable of gender where the male population was underestimated.
NL: Design weight and redressment weight; redressment was calculated to adjust for age, sex, position in household, education main activity, turnout and results in last national elections. Weights are rescaled to net sample size.
NO: No weighting procedure (in net sample younger people, single (never married) and people with lower education underrepresented.
NZ: The provided weighting variable weights the sample so its age-sex distribution matches that of the New Zealand population according to the 2006 census.
PH: Weighting variable is based on people aged 18 and above and region (NCR, Balance Luzon, Visayas, Mindanao).
PT: Design weight and redressment weight to adjust for non-response bias; variables used for calculating redressment weight: AGE, SEX, PT_DEGREE. Weights are rescaled to net sample size.
RU: Variables age, sex and education used for calculation of weight.
SK: Weight constructed according the population characteristics sex, age groups, education, ethnicity (nationality), size of community and region (males, younger and low educated respondents underrepresented).
TW: Weighting factor is designed on sex, age, urbanization and education degree groups. Weights were then generated to match the population characteristics of Taiwan area.
US: The weight variable takes into consideration the sub-sampling of non-respondents and the number of adults in the household (men and those under 25/ over 65 undersampled).
ZA: Personal and household weights are benchmarked using the SAS CALMAR macro and province, population group, gender and 5 age groups (i.e. 16-24, 25-34, 35-49, 50-50 and 60 and older) as benchmark variables for persons and province and population group of the respondent in the household for households as benchmark variables.
(en)
|
![[This page as RDF]](https://data.gesis.org/gesiskg/static/rdf-icon.gif){kind=icon}