Since 1975 the GSS has used full-probability sampling of households designed to give each household an equal probability of being included in the GSS. Hence, for household-level variables the GSS is self-weighting.
The data for each of the four years include three weight variables: ADULTS (Household Members 18 Yrs and Older), FORMWT (Post-Stratification Weight) and OVERSAMP (Weights for Black Oversamples). Since only one adult per household was interviewed, persons living in large households had a lower probability to be selected for the survey. For person-level variables, weighting statistical results in proportion to the number of persons over 18 in the household (variable ADULTS) can compensate for this. For all four years FORMWT and OVERSAMP have all cases equal to 1 in the dataset.
In addition, the variable SAMPCODE is provided for the convenience of persons who wish to study within-cluster and between-cluster variations in the GSS. More information about these variables is included in the Notes in the variable description of each variable.
ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:
Users are encouraged to read more about the General Social Survey on the
Terms of use are available at http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/35536/terms
AVAILABLE. This study is freely available to the general public.