Scottish Government

ANNEX A -TECHNICAL ANNEX

The Scottish Social Attitudes series

1. The Scottish Social Attitudes ( SSA) survey was launched by the Scottish Centre for Social Research (ScotCen) in 1999, following the advent of devolution. Based on annual rounds of interviews with around 1,500 people drawn using probability sampling (based on a stratified, clustered sample) ³⁶, its aims are to facilitate the study of public opinion and inform the development of public policy in Scotland. In this it has similar objectives to the British Social Attitudes ( BSA) survey, which was launched by ScotCen's parent organisation, the National Centre for Social Research (NatCen) in 1983. While BSA interviews people in Scotland, these are usually too few in any one year to permit separate analysis of public opinion in Scotland (see Park, et al, 2010 for more details of the BSA survey).

2. SSA has been conducted annually each year since 1999, with the exception of 2008. The survey has a modular structure. In any one year it typically contains four or five modules, each containing 40 questions. Funding for its first two years came from the Economic and Social Research Council, while from 2001 onwards different bodies have funded individual modules each year. These bodies have included the Economic and Social Research Council, the Scottish Government and various charitable and grant awarding bodies, such as the Nuffield Foundation and Leverhulme Trust.

The 2009 survey

3. The 2009 survey contained modules of questions on:

• Government and public services in Scotland (funded by the Scottish Government Office of the Chief Researcher from 2004-2007 and again in 2009)
• Anti-social behaviour (funded by the Scottish Government)
• What makes somewhere a good place to live, with a particular focus on the importance of greenspace (funded by the Scottish Government)
• Drugs and recovery from problem drug use (funded by the Scottish Government),
• National identity, in collaboration with David McCrone and Frank Bechhofer of the University of Edinburgh (funded by the Leverhulme Trust)
• Escape places and violence (funded by NHS Health Scotland), and
• Constitutional change (self-funded by ScotCen).

4. Findings from the modules funded by the Scottish Government will be available in reports published on their website ( www.scotland.gov.uk), while separate programmes of dissemination are planned for each of the other modules. This technical annex is designed to accompany Scottish Government reports based on SSA 2009. It covers the methodological details of the survey as well as further discussion of the analysis techniques used in the reports.

Sample design

5. The survey is designed to yield a representative sample of adults aged 18 or over, living in Scotland. The sample frame is the Postcode Address File ( PAF), a list of postal delivery points compiled by the Post Office. The detailed procedure for selecting the 2009 sample was as follows:

I. 102 postcode sectors were selected from a list of all postal sectors in Scotland, with probability proportional to the number of addresses in each sector for addresses in urban areas and a probability of twice the address count for sectors in rural areas (i.e. the last 3 categories in the Scottish Government's 6 fold urban-rural classification). Prior to selection the sectors were stratified by Scottish Government urban-rural classification ³⁷, region and percentage of household heads recorded as being in non-manual occupations ( SEG 1-6 and 13, taken from the 2001 Census).

II. 30 addresses were selected at random from each of these 102 postcode sectors

III. Interviewers called at each selected address and identified its eligibility for the survey. Where more than one dwelling unit was present at an address, all dwelling units were listed systematically and one was selected at random using a computer generated random selection table. In all eligible dwelling units with more than one adult aged 18 or over, interviewers had to carry out a random selection of one adult using a similar procedure.

Response rates

6. The Scottish Social Attitudes survey involves a face-to-face interview with respondents and a self-completion questionnaire, completed by around nine in ten of these people (89% in 2009). The numbers completing each stage in 2009 are shown in Table 1. See Bromley, Curtice and Given (2005) for technical details of the 1999-2004 surveys, Given and Ormston (2006) for details of the 2005 survey, Cleghorn, Ormston and Sharp (2007) for the 2006 survey and Ormston (2008) for the 2007 survey.

Table 1: 2009 Scottish Social Attitudes survey response

Notes to table
1 This includes empty / derelict addresses, holiday homes, businesses and institutions.
2 'Unknown eligibility' includes cases where the address could not be located, where it could not be determined if an address was residential and where it could not be determined if an address was occupied or not.
3 Refusals 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.
4 Non-contacts comprise households where no one was contacted after at least 6 calls and those where the selected person could not be contacted.
5 'Other non-response' includes people who were ill at home or in hospital during the survey period, people who were physically or mentally unable to participate and people with insufficient English to participate.

Weighting

7. All percentages cited in this report are based on weighted data. The weights applied to the SSA 2009 data are intended to correct for three potential sources of bias in the sample:

• Differential selection probabilities
• Deliberate over-sampling of rural areas
• Non-response.

8. Data were weighted to take account of the fact that not all households or individuals have 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. Differences between responding and non-responding households were taken into account using information from the census about the area of the address as well as interviewer observations about participating and non-participating addresses. Finally, the weights were adjusted to ensure that the weighted data matched the age-sex profile of the Scottish population (based on 2008 mid-year estimates from the General Register Office for Scotland).

Fieldwork

9. Fieldwork for the 2009 survey ran between late April and early September 2009. An advance letter was sent to all addresses and was followed up by a personal visit from a ScotCen interviewer. Interviewers were required to make a minimum of 6 calls at different times of the day (including at least one evening and one weekend call) in order to try and contact respondents. All interviewers attended a one day briefing conference prior to starting work on the study.

10. 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. Table 1 (above) summarises the response rate and the numbers completing the self-completion in 2009.

Analysis variables

11. Most of the analysis variables are taken directly from the questionnaire and to that extent are self-explanatory. These include age, sex, household income, and highest educational qualification obtained. The main analysis variables requiring further definition are set out below.

National Statistics Socio-Economic Classification ( NS- SEC)

12. The most commonly used classification of socio-economic status used on government surveys is the National Statistics Socio-Economic Classification ( NS- SEC). SSA respondents were classified according to their own occupation, rather than that of the 'head of household'. Each respondent was asked about their current or last job, so that all respondents, with the exception of those who had never worked, were classified. The seven NS- SEC categories are:

• Employers in large organisations, higher managerial and professional
• Lower professional and managerial; higher technical and supervisory
• Intermediate occupations
• Small employers and own account workers
• Lower supervisory and technical occupations
• Semi-routine occupations
• Routine occupations.

13. The remaining respondents were grouped as 'never had a job' or 'not classifiable'.

Scottish Index of Multiple Deprivation ( SIMD)

14. The Scottish Index of Multiple Deprivation ( SIMD) ³⁸ 2009 measures the level of deprivation across Scotland - from the least deprived to the most deprived areas. It is based on 38 indicators in seven domains of: income, employment, health, education skills and training, housing, geographic access and crime. SIMD 2009 is presented at data zone level, enabling small pockets of deprivation to be identified. The data zones are ranked from most deprived (1) to least deprived (6,505) on the overall SIMD 2009 and on each of the individual domains. The result is a comprehensive picture of relative area deprivation across Scotland.

15. The analysis in this report used a variable created from SIMD data indicating the level of deprivation of the data zone in which the respondent lived in quintiles, from most to least deprived. ³⁹

Analysis techniques

Regression

16. Logistic regression models are used to assess whether there is reliable evidence that particular variables are associated with each other.

17. 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. This technique takes into account relationships between the different independent variables (for example, between education and income, or area deprivation 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.

Chapter 2 regressions

18. Chapter Two of this report uses logistic regression - a method that summarises the relationship between a binary 'dependent' variable (one that takes the values '0' or '1') and one or more 'independent' explanatory variables. The tables that follow show how the odds ratios for each category in significant explanatory variables compares to the odds ratio for the reference category (always taken to be 1.00).

19. In Chapter 2, the regression analysis uses a dependent variable based on whether or not people had a below average score on the question on how satisfied people are with their area as a place to live. If the respondent gave their satisfaction with their local area a score between 0 and 6 on the 11-point scale, the dependent variable takes a value of 1. If not, it takes a value of 0. An odds ratio of above 1 means that, compared with respondents in the reference category, respondents in that category have higher odds of having a below average score for local area satisfaction. Conversely, an odds ratio of below 1 means they have lower odds of thinking this than respondents in the reference category.

20. For example, if we look at household income, we can see that people in all categories with an income above £12,000 per annum have odds ratios of less than 1, indicating that they have lower odds of having a below than average score on local area satisfaction than those in the reference category (i.e. people with a household income of £11,999 or less).

21. A 'p' value is the probability of the observed result occurring due to chance alone. A p-value of 0.05 or less indicates that there is less than a 5% chance we would have found such a difference just by chance if in fact no such difference exists, while a p-value of 0.01 or less indicates that there is a less than 1% chance. P-values of 0.05 or less are generally considered to indicate that the difference is highly statistically significant, while a p-value of 0.06 to 0.10 may be considered marginally significant.

22. The regression was conducted in stages as its main aim was to identify what additional contribution each of the five different types of factors made in relation to understanding people's level of satisfaction. Building up the analysis in layers helps to meet this aim.

23. The final regression model reported below was produced following a process involving the following stages of analysis:

1. First, forward stepwise regression analysis was conducted in SPSS 15.0. The variables entered into these initial models are noted below the final model, below.

2. Second, those variables found to be significantly associated with the dependent variable by these SPSS forward stepwise models were entered into final regression models run through CS Logistic in SPSS. Unlike forward stepwise regression analysis in SPSS 15.0, CS Logistic can account for complex sample designs (in particular, the effects of clustering and associated weighting) when calculating odds ratios and determining significance. The models shown below include only those variables found to be significant after the regression models were run using CS Logistic in SPSS.

3. Five models were run for one dependent variable - first a model was run including individual and household level factors only, then a second model was run including significant factors from the first stage plus area level factors. The third stage then took all the factors significant after the second stage and added in the social trust and community cohesion measures. The fourth stage took the significant factors from the third stage and added in feelings about specific aspects of the local area. The fifth stage took the significant factors from the fourth stage and added in the factors that people think are most in need of improvement in their area. Running the analysis in these stages allowed for the exploration of how much each additional set of factors added to the ability to explain the dependent variable.

4. As more than one model was created for one dependent variable, only the final model has been reported below. These include significant factors after all the various demographic and attitudinal variables listed have been taken into account. Copies of any additional models are available from ScotCen on request.

24. The table of Model 1 below presents the full results of the final analysis stage. It illustrates the association between each factor and satisfaction once all other factors had also been taken into account.

Regression model

Model 1 - Chapter 2: Satisfaction with local area as a place to live

Cases included in model = 1,241

This is the final CS Logistic model, including all significant factors.

Independent variables included in initial forward stepwise models in SPSS:

Individual and household factors: gender, age, education, household income, type of accommodation, tenure, having children living in the household and having a long-term illness or disability

Area-level factors: urban rural classification, area deprivation

Social trust

Feelings about specific aspects of the local area:

• Availability around here of somewhere green and pleasant to walk or sit
• How easy it is to get around your area on foot
• Availability around here of places that are safe and pleasant for children to play
• How much you would agree or disagree that 'this is a nice area to walk around in'
• How good or bad an area this is for cycling
• How much graffiti or vandalism they have seen in their area in the last 12 months
• How much rubbish or litter they have seen in their area in the last 12 months
• How much noise they have heard from neighbours or loud parties in their area in the last 12 months
• How big a problem discarded needles or syringes lying around is in their area

Things that are in most need of improvement: 1st and 2nd choices combined

Chapter Four regressions

25. This section provides additional detail about the analysis conducted to inform the findings presented in Chapter Four. For each of the four 'dependent' variables of interest (self-reported health, overall satisfaction with life, level of social trust and degree of community cohesion), analysis was undertaken in a number of stages.

26. First, in each case we established the relationship between the relevant dependent variable (that is self-reported health, etc.) and both (i) the individual level socio-economic characteristics of respondents, and (ii) the character of the area in which someone lives (as measured by the Scottish Index of Multiple Deprivation). We then assessed whether satisfaction with the quality of the nearest green or open space was associated with the dependent variable after taking into account the role of those individual and area level factors.

27. Next, we considered the specific importance of satisfaction with the nearest green or open space as compared with satisfaction with the local area more generally. This was achieved by examining whether any relationship between satisfaction with the quality of the nearest greenspace and the relevant dependent variable is maintained even after we also introduce a measure of satisfaction with the area in which the respondent lives.

28. Finally, we attempted to assess which particular aspects of local greenspace are important by examining which, if any, of seven specific aspects related to local greenspace as assessed by respondents (alongside their degree of satisfaction with the nearest greenspace) were linked to the dependent variable. These seven aspects were introduced in Chapters Two and Three. They are:

• The availability locally of somewhere green and pleasant to walk and sit
• The availability locally of places that are safe and pleasant for children to play
• Whether the local area is nice to walk around in
• How far away the nearest green or open space is.
• How often the respondent visits their nearest green or open space.
• The type of green or open space that is nearest the respondent (public park, beach, etc.)
• The main reason given for visiting the nearest green or open space.

29. This analytic strategy was pursued by undertaking for each dependent variable the following sequence of multivariate modelling:

(a) Introduced those individual level demographic variables that were expected to be significantly associated with the dependent variable,

(b) added SIMD to this model and assessed whether it was significant

(c) added satisfaction with quality of the nearest green or open space and assessed whether it was significant if added at this stage

(d) if it was significant, we examined whether this remained the case after general satisfaction with the local area as a place to live was added to the model

(e) used a stepwise procedure to identify which, if any, of the more specific assessments of the quality of local greenspace (together with satisfaction with the nearest greenspace) were significantly associated with the dependent variable after inclusion of those variables that were significant at step (b),

(f) added general satisfaction with the local area to this model in order to establish which, if any, of the specific evaluations of greenspace remained significant.

30. This strategy was pursued primarily using ordinary logistic regression, with a relationship being deemed significant at the 5% level of probability. However, in assessing the statistical significance of its results, this ordinary logistic regression assumes that the characteristics and attitudes of each respondent are wholly independent of the characteristics and attitudes of all other respondents. In practice this is not strictly true of respondents to the Scottish Social Attitudes survey; respondents are drawn from randomly selected clusters of areas (postcode sectors), rather than wholly at random from across Scotland as a whole. This is necessary in order to reduce the travel time between addresses to make the fieldwork cost effective, and is common practice across most face-to-face surveys, with the exception of those with very large samples and continuous fieldwork. Those respondents who live in the same area share the same local environment and greenspace, and thus can be expected to give somewhat similar answers. As a result the probability that any relationships we uncovered were the product of chance rather than being a reflection of the true position across Scotland as a whole was increased. This increased probability can be taken into account by using a more complex version of logistic regression that takes the geographical clustering of our respondents into account. ⁴⁰ We therefore applied this more complex procedure at steps (d) and (f) in order to affirm which of the relationships we uncover at those two stages can reasonably be regarded as indicative of the position across Scotland as a whole.

References in technical annex

Park et al (eds.) (2010) British Social Attitudes: the 26th Report, London: Sage

Bromley, C., Curtice, J., and Given, L. (2005) Public Attitudes to Devolution: the First Four Years, London: The National Centre for Social Research.

Given, L and Ormston (2006) Scottish Social Attitudes survey 2005: Scottish Executive Core module - technical report, Scottish Executive Social Research.

Cleghorn, N, Ormston, R & Sharp, C (2007) Scottish Social Attitudes survey 2006: Core module technical report, Scottish Executive Social Research.

Ormston, R (2008) Scottish Social Attitudes Survey 2007 Core module: Report 1 - Attitudes to government in Scotland, Scottish Government Social Research.