Scottish Surveys Core Questions 2022

1.3 Weighting

Datasets from the three source surveys were combined into new SSCQ datasets (see Table 1): SSCQ household variables (19,671 responses), SSCQ individual variables (19,545 responses) and SSCQ crime variables (18,082 responses). Due to the smaller number of interviewees responding to the self-completion part of the SHeS, the number of responses to the SSCQ individual variables is slightly lower for mental wellbeing, veteran status and sexual orientation (see section 1.6).

SSCQ household variables are household type, tenure and car access.

SSCQ individual variables are self-assessed general health, limiting long-term health conditions, smoking, unpaid care provision, mental wellbeing, highest achieved qualification, economic activity, country of birth, ethnic group, religion, veteran status, marital status, sexual orientation, sex and age.

SSCQ crime variables are perception of local crime rate and six questions on perceptions of police performance.

Each variable response category (i.e., household, individual, crime) in each of the surveys carries a different design effect. If we were solely seeking the most efficient estimate for each variable separately, then separate scale factors could be derived for each one. However, this would restrict the use of the dataset. Rather, for each constituent survey dataset the design effects were estimated for each category and then the median design effect over all categories was used as the representative design effect of that survey. These design effects were then used along with the sample sizes to calculate the effective sample sizes (neff) and scaling factors for combining the three datasets.

Table 1: Numbers of sample and effective sample pooled from the source surveys

To combine the data, the scale factors were applied to the grossing weights for the individual surveys (described in section 1.1). The neff of each survey contribution formed the basis for the scaling factors:

survey A weight scaling factor = neff (surveyA) / (sum of three survey neffs).

The weights were then re-scaled to be proportionate to the effective sample size contribution of each survey and used as pre-weights. The three pooled SSCQ datasets were then weighted again to be representative across Scotland. For the SHS and SCJS, this is the total estimated population in Scotland. For the SHeS, this is the estimated population of Scotland living in private households. In order to include the SHeS survey data in the SSCQ, new pooled weights were calculated to make the data representative to this higher number, the total population of Scotland.

As a result of this (together with some differences in the way that ‘refused’ and ‘don’t know’ responses are dealt with, which are described in section 1.7), the SHeS figures included in the SSCQ will be different to those published by the SHeS, because the data has been weighted to different population totals. Users should refer to the individual surveys for the key national indicators but may use the SSCQ for break-downs by equality groupings and small areas.

SSCQ 2022 Weighting Bases are published in the Supporting Documents section on the website.