« Previous | Contents | Next »
Listen
ANNEX 2 METHODOLOGY
Conduct of the research
A2.1 The 2006 SCVS was carried out by BMRB Social Research, with interviews being conducted between June and December 2006. Full details on the 2006 SCVS methodology are provided in the technical report.
Response rates
A2.2 The 2006 SCVS interviewed 4,988 adults aged 16+ and achieved a response rate of 70 per cent. Of those who completed the main survey, 4,701 agreed to take part in the self-completion questionnaire. This is equivalent to a response rate of 66 per cent of all issued sample and 94 per cent of all those interviewed. The drugs module of the self-completion was, however, only asked of respondents aged 16 to 59; of which 96 per cent agreed to complete the section.
Sampling and weighting
A2.3 The 2006 SCVS, like previous sweeps of the survey, employed a probability sample with a multi-stage stratified design. Households were randomly selected from the Postcode Address File ( PAF). Sample points were clustered within postcode sectors but were spread across the whole of Scotland (including the Highlands and larger islands). Once households had been selected, one respondent was randomly selected from all the adults aged 16+ who were resident at the address (using the Kish grid method). No substitution of households or selected individuals was permitted.
A2.4 Weighting was applied to the main survey data in order to compensate for any bias which might have arisen from either variability in sample selection probabilities (such as a weight to compensate for the number of dwelling units found within a particular address) or non-response. Non-response weights were calculated by comparing the survey data with national population estimates. The self-completion data was subject to the same potential for biases as the main survey data and as such the weights calculated for the main survey data were also applied to the self-completion data. Since the overall response rate to the self-completion questionnaires was slightly lower than the main survey there was additional scope for bias arising from non-response to the self-completion element. In the previous sweep of the survey in 2004 an additional weight was calculated to compensate for this. However, a comparison of the weighted profile of all adults completing the self-completion part of the survey in 2006 with that of the adult population suggested that no additional weighting was necessary.
Self-completion questionnaire
A2.5 The 2006 self-completion questionnaire is included in Annex 3.
A2.6 On completion of the main interview respondents were asked if they would be willing to complete the final section of the survey on their own by entering their answers directly into the laptop. Respondents aged 16-59 completed the drugs module followed by a module on experience of domestic violence; those aged 60 or over proceeded straight to the domestic violence module. Respondents were offered the laptop and asked to follow the instructions on screen and enter their answers appropriately. Practice questions were included before the start of the self-completion module to give the interviewer an opportunity to show the respondent the different functions of the computer. If the respondent was unable or unwilling to complete the modules using the computer the interviewer could administer the self-completion.
« Previous | Contents | Next »