ATTITUDES TO DISCRIMINATION IN SCOTLAND
APPENDIX TWO TECHNICAL DETAILS OF THE SURVEY
The data in the report are taken from a module of questions asked in the 2002 Scottish Social Attitudes Survey. The survey involved a face-to-face interview with 1665 respondents and a self-completion questionnaire completed by 1507 (91%) of these people. The discrimination module questionnaire can be found in Appendix Three, details of the other questions in the survey can be obtained from NatCen at www.natcen.ac.uk . The following summarises the technical aspects of the survey, for more details see Bromley et al (2003).
The survey was designed to yield a representative sample of adults aged 18 or over living in Scotland. The sample frame was the Postcode Address File (PAF), a list of postal delivery points compiled by the Post Office. The sample design involved three stages:
1. Eighty-three postcode sectors were selected from a list of all postal sectors in Scotland, with probability proportional to the number of addresses in each sector. Prior to selection the sectors were stratified by region, population density, and percentage of household heads recorded as employers / managers (taken from the 1991 Census). The list was also stratified using the using the Scottish Household Survey (SHS) six-fold classification of urban and rural areas 14, and sectors within rural and remote categories were over-sampled.
2. Thirty one addresses were selected at random from 68 sectors located within the first three SHS urban-rural classifications (large urban areas, to accessible small towns), while 60 addresses were selected from the remaining 15 sectors within the three most rural categories (remote small towns to remote rural areas).. This was done in order to boost the number of respondents from remote and rural areas. In total the issued sample consisted of 3,039 addresses.
3. Interviewers called at each selected address, identified its eligibility for the survey, and where more than one household was present at an address listed all households systematically and selected one at random using a computer generated random selection table. In all eligible households with more than one adult aged 18 or over, interviewers also had to carry out a random selection of one adult using a similar procedure.
Data were weighted to take account of the fact that not all households or individuals had the same probability of selection for the survey. For example, adults living in large households have a lower selection probability than adults who live alone. Weighting was also used to correct the over-sampling of rural addresses. All the percentages presented in this report are based on weighted data, the unweighted sample sizes are shown in the tables.
Interviewing was carried out between June and October 2002, (more than 80% being completed by the end of August). An advance letter was sent to all addresses and was followed up by a personal visit from a NatCen interviewer. All interviewers attended a one day briefing conference prior to starting work.
Interviews were conducted using face-to-face computer-assisted interviewing (a process which involves the use of a laptop computer, with questions appearing on screen and interviewers directly entering respondents' answers into the computer). All respondents were asked to fill in a self-completion questionnaire which was either collected by the interviewer or returned by post. A total of 158 respondents (9%) did not complete a questionnaire. Table A2-1 summarises the response rate.
Table A2-1 Details of response to 2002 Scottish Social Attitudes survey
Vacant, derelict and other out of scope 1
Interview not achieved
Unknown eligibility 4
Notes to table
1This included empty / derelict addresses, holiday homes, businesses and institutions.
2Refusals include refusals prior to selection of an individual, refusals to the office, refusal by the selected person, 'proxy' refusals made by someone on behalf of the respondent and broken appointments after which a respondent could not be re-contacted.
3Non-contacts comprise households where no one was contacted after at least 4 calls and those where the selected person could not be contacted.
4 ' Unknown eligibility' includes cases where the address could not be located, where it could not be determined if an address was a residence and where it could not be determined if an address was occupied or not.
Table A2-2 Cell Sizes for Categories in Sections 4 and 5
Once a week
38,000 or more
9,999 or less
Self-rated economic hardship
Coping on income
Having difficulty on income
Where respondent would prefer to live
With different kinds of people
In an area where people are the same
Cell numbers for tables in Chapters 4 and 5
The following table shows the total number of respondents in the survey which fall into one of the categories for which statistics are quoted extensively in sections 4 and 5. Note that where a question was included in the self-completion questionnaire the total number of respondents on which a statistic is based is a little lower than quoted here.
Data interpretation: statistical modelling
For the more complex analysis in this report we have used logistic regression models to assess whether there is reliable evidence that particular variables are associated with each other.
Regression analysis aims to summarise the relationship between a 'dependent' variable and one or more 'independent' explanatory variables. It shows how well we can estimate a respondent's score on the dependent variable from knowledge of their scores on the independent variables. The technique takes into account relationships between the different independent variables (for example, between education and income, or social class and housing tenure). Regression is often undertaken to support a claim that the phenomena measured by the independent variables cause the phenomenon measured by the dependent variable. However, the causal ordering, if any, between the variables cannot be verified or falsified by the technique. Causality can only be inferred through special experimental designs or through assumptions made by the analyst. All regression analysis assumes that the relationship between the dependent and each of the independent variables takes a particular form. In logistic regression, the form of regression analysis used in this report, it is assumed that the relationship can be adequately summarised by an S-shaped curve. where the impact on the dependent variable of a one-point increase in an independent variable becomes progressively less the closer the value of the dependent variable approaches 0 or 1.
Factor analysis is a statistical technique which aims to identify whether there are one or more apparent sources of commonality to the answers given by respondents to a set of questions. It ascertains the smallest number of factors (or dimensions) which can most economically summarise all of the variation found in the set of questions being analysed. Factors are established where respondents who give a particular answer to one question in the set tend to give the same answer as each other to one or more of the other questions in the set. The technique is most useful when a relatively small number of factors is able to account for a relatively large proportion of the relationships among all of the questions in the set.
The technique produces a factor loading for each question on each factor. Where questions have a high loading on the same factor then it will be the case that respondents who give particular answer to one of these questions tend to give a similar answer to the other questions. Chapter 4 makes particular use of factor analysis.
Full technical details of regression can be found in many textbooks on social statistics, for example Bryman and Cramer (1997).