Scotland's People Volume 7: results from the 2001/2002 Scottish Household Survey
In 2002, the Scottish Household Survey continued to develop and also to enjoy the support of a wide variety of people through their contribution to the work of the survey or by their use and disseminate of the survey findings. Once again, as the survey contractors, we are grateful for this continuing support.
Although their composition has changed somewhat, the ongoing support of the Advisory Group and Technical Group remains a vital ingredient in the success of the survey. These groups also play a major role in promoting the dissemination of the survey findings and the use of the data within the Scottish Executive and in the wider policy and research communities. The dissemination of the SHS has resulted in considerable growth in the use of the data to examine important policy issues. The questionnaire used in the survey during 2001 and 2002 contained a number of changes that reflect emerging policy issues and the commitment of everyone involved in the survey to ensure that the SHS makes a major contribution to informed policy-making.
The survey is overseen by an Advisory Group and a Technical Group, who are, in turn, supported by the SHS Network Group which consists of a broad network of administrators, researchers and statisticians from the Scottish Executive and representatives of CoSLA, Scottish Homes and the General Register Office for Scotland. We are grateful for their support. In particular, the research team would like to thank Katherine Hudson, Ruth Bryan and Esta Clark for their continuing support and guidance throughout 2002 and for their assistance and patience in the drafting of this report.
In spite of all this support, any errors that may remain in this report are, of course, our own.
NFO Social Research
1. Background to the survey
The Scottish Household Survey (SHS) is a continuous survey based on a sample of the general population in private residences in Scotland. The survey started in 1999 and is financed by the Scottish Executive and undertaken by a partnership of NFO Social Research and MORI Scotland.
The aim of the survey is to provide representative information about the composition, characteristics and behaviour of Scottish households, both nationally and at a more local level. The survey covers a wide range of topics to allow links to be made between different policy areas. There is a particular focus on information to inform policy on Transport, Social Justice and Housing. Results are reported in a series of bulletins of which there have been eight, annual reports, of which this is the fourth 1 and a number of other Scottish Executive publications, some of which are listed on page 189.
This Annual Report is based on data collected from 30,639 households and 28,685 individuals in 2001 and 2002.
The sample for the survey meets a number of criteria. It is designed to provide nationally representative samples of private households and of the adult population in private households. This is achieved by splitting the interview between a household respondent and an adult selected at random from the permanent residents of the household.
In order to meet the reporting requirements, the sample is structured to be nationally representative each quarter and to provide a representative sample for larger local authorities each year (those with over 750 achieved interviews per year).
The sample is also designed to provide data for each local authority over a two-year period. This is achieved by disproportionately sampling in each local authority to achieve a target of at least 550 interviews over two years (equivalent to a simple random sample of 500, with a likely maximum sampling error of 4%).
The survey uses two different sampling approaches. In areas of high population density (Glasgow, Edinburgh, Aberdeen, Dundee, etc) a simple random sample of dwellings is selected covering the entire two-year sample period. These are subsequently clustered into interviewer allocations. In areas of lower population density, Census enumeration districts (EDs) are selected with probability proportionate to population. In each ED, 18 addresses are selected, based on achieving an average of 11 interviews from each sampling point.
The sample is selected from the small user Postcode Address File (PAF) for Scotland, expanded to take account of addresses which might only be listed once but actually contain multiple dwellings, such as tenement blocks and multi-storey flats. Although the small user PAF excludes many institutional addresses such as student halls of residence or nurses' homes, there are no geographical exclusions from the survey, which covers all parts of Scotland, including the Highlands and Islands.
The survey questionnaire is in two parts. A householder or the spouse/partner of a householder completes Part 1 of the interview. Once the composition of the household has been established, one of the adults in the household is randomly selected by the computer to complete Part 2. 2 In all households with a single adult the same person completes both parts but as the number of adults in the household increases, the probability of the random adult being the same as the household respondent declines. 3
The household section of the interview deals with topics such as household composition, housing and tenure, health, access to the internet, the vehicles available to the household, the occupation and industry of the highest income householder, household income and housing costs. The random adult section deals with individuals' housing change, tenure change, neighbourhood problems, transport and use of the internet, public transport, public services, income and employment.
Mode of interview
Interviewing is conducted using Computer Assisted Personal Interviewing (CAPI). Instead of using pen and paper to record responses, data is collected on handheld or laptop computers.
After excluding addresses that were outwith the scope of the survey 4, the overall response rate for this two-year sweep of the survey was 67%. There was significant variation in response between local authorities. The highest response rate was achieved in Eilean Siar (81%) and the lowest response was achieved in Edinburgh 60%. Post-survey weighting takes account of both the disproportionate sampling between local authorities and the differential response between authorities.
The data presented in the report have been weighted in one of two ways. Household data (collected in part one of the interview) are weighted to take account of the disproportionate sampling and response between local authorities. Random adult data (from part two) are weighted to reflect both the disproportionate sampling and response to part two between local authorities and the different probabilities of selection within households. 5 These weighted data have been compared with other official estimates and no additional weighting has been undertaken at this stage.
Full details of the survey can be obtained from the companion Technical Report of the survey. 6 This contains full details of the sampling, questionnaire, fieldwork, response rates and weighting.
Structure of the Annual Report
The report is divided into five substantive chapters, as follows:
Chapter 3 - 'Who we are' - provides information on the population of Scotland covering topics such as the age and sex of the population, household size and type and the marital status of household members.
Chapter 4 - 'Where we live' - looks at the housing circumstances of the population. It covers housing tenure, tenure change, moving home, and the types of properties in which people live.
Chapter 5 - 'What we do' - examines the economic circumstances of households and adults. It looks at whether people work, the types of work they do, and the number of hours they work. It also looks at the circumstances of non-working adults and the situation of women of working age.
Chapter 6 - 'How we live' - presents analysis of household resources, including both material and financial resources. It examines ill health and disability, and the provision and receipt of care.
Chapter 7 - 'Our communities' - analyses adults' involvement in their community. This includes voluntary activity and looks at adults' views of local services including their contact with, use of, and satisfaction with, local services.
The report also contains a glossary with detailed definitions of some of the terms used in the survey. This sets out what is meant by terms such as 'Highest Income Householder' and what is included and excluded from, for example, household income.
2. Using the information in this report
How data is displayed in tables
All tables are presented in the format "dependent variable by independent variable" where the independent variable is being used to examine or explain variation in the dependent variable. Thus, a table titled 'housing tenure by household type' shows how housing tenures vary among different household types. Where the tables show column percentages, the dependent variable is shown in the rows and the columns show the independent variable. Where the tables show row percentages, this is switched and the dependent variable is shown in the columns.
All tables have a descriptive and numerical base showing the population or population sub-group examined in it. While all results have been calculated using weighted data, the bases shown give the unweighted counts. It should therefore be noted that the results and bases presented cannot be used to calculate how many respondents gave a certain answer.
In general, percentages in tables have been rounded to the nearest whole number. Zero values are shown as a dash (-), values greater than zero but less that 0.5% are shown as zero and values of 0.5% but less than 1% are rounded up to 1%. Columns or rows may not add to 100% because of rounding or where multiple responses to a question are possible.
In some tables, percentages have been removed from columns and replaced with '*' where the base on which percentages would be calculated is less than 100. This data is judged to be insufficiently reliable for publication.
Variations in base sizes for tables
Because the questionnaire is administered using CAPI, item non-response is kept to a minimum. Bases occasionally fluctuate slightly due to small amounts of missing information (where, for example, the age or sex of household members has been refused and where derived variables such as household type use this information).
Some questions apply only to individual survey years and the bases are correspondingly lower. Occasionally, questions are introduced in the course of a survey year and again the base size is lower.
In general, only tables that contain the full survey bases - 30,639 households, 70,453 household members or 28,685 adults should be used as the source of percentages for the dependent variable in a table since missing data will change the percentages in the "All" column or row. The sample base appendix gives details of frequencies and bases for the main dependent variables.
One section of the questionnaire is substantially affected by missing information. In the section on household income, approximately 33% of respondents either refuse to answer the questions or are unable to provide information that is sufficiently reliable to report, for example, because there are no details of the level of income received for one or more components of their income. After the survey, statistical analysis of the characteristics of households where income is available allows income data to be imputed for households where income data is missing. After imputation, missing income data is reduced to only 3% of households (see Glossary for more details).
The income information in the report includes the income of the Highest Income Householder and their spouse or partner (where there is one). Income from employment, pensions and benefits and income from other sources is included. The income of other household members is only included if it represents 'other' income for the HIH or spouse i.e. the other household member contributes to household resources by paying 'dig money'.
The current income information collected through the SHS, is only intended to provide estimates by income band. The survey asks for income only for use as a "background" variable when analyzing other topics, or for selecting the data for particular sub-groups of the population (such as the low paid) for further analysis. The SHS cannot be used as a source of figures on average income or average earnings.
Where reference is made in the text to differences between sub-groups of the sample, these differences have been tested and found to be significant at the 95% confidence limits. 7
All survey data has a degree of error associated with it because it is based on a sample of the population. Any proportion measured in the survey has an associated sampling error, usually expressed as x% at the 95% confidence limits. Technically, all results should be quoted in this way. For example, based on the survey results we can be 95% confident that between 24.3% and 25.7% of households own their property outright. However, it is less cumbersome to simply report the percentage as 25% (see Table 2. 1). Where sample sizes are small or comparisons are made between sub-groups of the sample, the sampling error needs to be taken into account. There are formulae to calculate whether differences are statistically significant (i.e. they are unlikely to have occurred by chance) and Appendix 1 provides a simple way to estimate if differences are significant.
The ethnicity question in the SHS does not fully replicate the full wording of the Census question. As a consequence, while the Census clearly groups cultural categories within racial groupings, the SHS does not make such clear distinctions, and thus, in the SHS, some non-white respondents may have classified themselves with the Scottish/British groupings and some white respondents may have classified themselves outside these categories. The SHS definition of ethnicity is discussed more fully in the technical report.