General Social Survey: Summary Results, Australia methodology

This is not the latest release View the latest release
Reference period
2014
Released
29/06/2015

Explanatory notes

Introduction

1 This publication presents summary results on a range of social dimensions, compiled from the 2014 General Social Survey (GSS). The survey collected information about personal and household characteristics for people aged 15 years and over resident in private dwellings across Australia (excluding very remote and people living in discrete Aboriginal and Torres Strait Islander communities), from March to June 2014.

2 The 2014 GSS collected data on a range of social dimensions from the same individual to enable analysis of the interrelationships in social circumstances and outcomes, including the exploration of multiple advantage and disadvantage experienced by that individual. The 2014 GSS is the fourth in the series, with the first GSS conducted in 2002, and again in 2006 and 2010. It is planned to repeat the survey at regular intervals (currently four-yearly). Each cycle of the GSS collects comparable information to allow for analysis of changes over time. The scope of the 2014 GSS was increased to include sample from the 15 to 17 year age group to aid better understanding of the outcomes for this population group. A cyclical component is also included to collect additional information on emerging or important topics of social concern. The cyclical component of the 2014 GSS included an expanded section on voluntary work.

Dimensions included in the 2014 GSS

3 The 2014 GSS collected information about:

  • demographic characteristics
  • housing and mobility
  • education (includes parental education)
  • employment
  • transport and mobility
  • subjective well-being and general life satisfaction measures
  • health and disability
  • difficulty accessing service providers
  • family and community involvement
  • social networks and participation
  • experiences of homelessness
  • voluntary work
  • crime and feelings of safety
  • sports attendance and participation
  • attendance at selected cultural and leisure venues
  • information technology
  • financial stress, resilience and exclusion
  • income
  • housing
  • assets and liabilities
  • discrimination
  • visa status
  • sexual orientation.
     

4 A full list of the data items from the 2014 GSS is available in the Data downloads section.

Scope of the survey

5 Only people who were usual residents of private dwellings in Australia were covered by the GSS. Private dwellings are houses, flats, home units and any other structures used as private places of residence at the time of the survey. People who usually reside in non-private dwellings such as hotels, motels, hostels, hospitals and short-stay caravan parks were not included in the survey. Usual residents are those who usually live in a particular dwelling and regard it as their own or main home. Visitors to private dwellings are not included in the interview for that dwelling. However, if they are a usual resident of another dwelling that is in the scope of the survey, they have a chance of being selected in the survey or, if not selected, they will be represented by similar persons who are selected in the survey.

6 The GSS was conducted in both urban and rural areas in all states and territories, except for very remote parts of Australia and discrete Indigenous communities. This exclusion is unlikely to impact on national estimates, and will only have a minor impact on any aggregate estimates that are produced for individual states and territories, except the Northern Territory where the excluded population accounts for over 20% of persons.

7 The Australian population at June 2014, after exclusion of people living in non-private dwellings, very remote areas of Australia and discrete Aboriginal and Torres Strait Islander communities was 22,828,900, of which 18,463,700 were aged 15 years and over.

8 The following people were excluded from resident population estimates used to benchmark the survey results, and were not interviewed:

  • diplomatic personnel of overseas governments
  • members of non-Australian defence forces (and their dependants) stationed in Australia
  • persons whose usual place of residence was outside Australia
  • visitors
  • persons living in very remote areas
  • persons living in discrete Aboriginal and Torres Strait Islander communities.
     

Sample design

9 The GSS was designed to provide reliable estimates at the national level and for each State and Territory. The sample was therefore spread across the states and territories in order to produce estimates that have a relative standard error (RSE) of no greater than 10% for characteristics that are relatively common in the national population (that at least 10% of the population would possess).

10 For the 2014 cycle, in order to be consistent with the aim of exploring the relative outcomes of people more vulnerable to socio-economic disadvantage, the sampling methodology was adapted to target sample from low socio-economic areas. People in these areas had a higher probability of being selected in the sample. Households were then randomly selected from each selected area to participate in the survey.

11 The initial sample for the survey consisted of approximately 18,574 private dwellings. This number was reduced to approximately 16,145 dwellings due to the loss of households which had no residents in scope for the survey and where dwellings proved to be vacant, under construction or derelict. Of the eligible dwellings, 80.1% responded fully (or adequately) which yielded a total sample from the survey of 12,932 dwellings.

12 Some survey respondents provided most of the required information, but were unable or unwilling to provide a response to certain data items. The records for these persons were retained in the sample and the missing values were recorded as 'don't know or not stated'. No attempt was made to deduce or impute for these missing values. Details of missing values for data items are presented in paragraph 31.

Data collection

13 ABS Interviewers conducted personal interviews using a Computer Assisted Interviewing (CAI) questionnaire at selected dwellings during the period March to June 2014. CAI involves the use of a notebook computer to record, store, manipulate and transmit the data collected during interviews.

14 Much of the detail obtained from the GSS was provided by one person aged 15 years or over, randomly selected from each participating household. The random selection of this person was made once basic information had been obtained about all household members. Some financial and housing items collected in the GSS required the selected person to answer on behalf of other members of the household. In some cases, particularly where household information was not known by the selected person, a spokesperson for the household was nominated to provide household information.

Weighting, benchmarking and estimation

Weighting

15 Weighting is the process of adjusting results from a sample survey to infer results for the total in-scope population whether that be persons or households. To do this, a 'weight' is allocated to each sample unit i.e. a person or a household. The weight is a value which indicates how many population units are represented by the sample unit.

16 The first step in calculating weights for each person or household is to assign an initial weight, which is equal to the inverse of the probability of being selected in the survey. For example, if the probability of a person being selected in the survey was 1 in 600, then the person would have an initial weight of 600 (that is, they represent 600 people).

Benchmarking

17 The initial weights are then calibrated to align with independent estimates of the population of interest, referred to as 'benchmarks'. Weights calibrated against population benchmarks ensure that the survey estimates conform to the independently estimated distribution of the population rather than to the distribution within the sample itself. Calibration to population benchmarks helps to compensate for over or under-enumeration of particular categories of persons which may occur due to either the random nature of sampling or non-response.

18 The GSS was benchmarked to the in scope estimated resident population (ERP) and the estimated number of households in the population. The 2014 GSS used population and household benchmarks based on the 2011 Census.

19 Given that the GSS did some targeting towards low socio-economic areas, further analysis was undertaken to ascertain whether benchmark variables, in addition to geography, age, and sex, should be incorporated into the weighting strategy. Analysis showed that the standard weighting approach did not adequately compensate for differential undercoverage in the 2014 GSS sample for SEIFA, when compared to other ABS surveys. As this variable was considered to have possible association with social characteristics, an additional benchmark was incorporated into the weighting process.

20 The benchmarks used in the calibration of final weights for the 2014 GSS were:

  • Persons
    • state by part of state by age by sex
    • SEIFA.    
       
  • Households
    • state by part of state by household composition
    • SEIFA.
       

Estimation

21 Survey estimates of counts of persons are obtained by summing the weights of persons or households with the characteristic of interest. Estimates for means, such as mean age of persons, are obtained by summing the weights of persons in each category (e.g. individual ages), multiplying by the value for each category, aggregating the results across categories, then dividing by the sum of the weights for all persons.

22 The majority of estimates shown in this publication are based on benchmarked person weights. The estimates in Table 15 however, are based on benchmarked household weights.

Seasonal effects

23 The estimates in this publication are based on information collected from March to June 2014, and due to seasonal effects they may not be fully representative of other time periods in the year. For example, the GSS asked standard ABS questions on labour force status to determine whether a person was employed. Employment is subject to seasonal variation through the year. Therefore, the GSS results for employment could have differed if the GSS had been conducted over the whole year or in a different part of the year.

Equivalised gross household income

24 The economic wellbeing of individuals is largely determined by their command over economic resources. People's income and reserves of wealth provide access to many of the goods and services consumed in daily life. The amount of income to which they have access is an important component of these resources. And while income is usually received by individuals, it is normally shared between partners in a couple relationship and with any dependent children. To a lesser degree, there may be sharing with other members of the household. Even when there is no transfer of income between members of a household, nor provision of free or cheap accommodation, members are still likely to benefit from the economies of scale that arise from the sharing of dwellings. Therefore, the income measures shown in this publication relate to household income.

25 Gross household income can be used as an indicator of whether a person has a relatively high or low level of economic wellbeing. However, larger households normally require a greater level of income to maintain the same standard of living as smaller households, and the needs of adults are normally greater than the needs of children. Equivalised household income estimates are estimates which have been adjusted by equivalence factors which standardise the income estimates with respect to household size and composition. Therefore, estimates of equivalised gross household income are used in this publication as a more relevant indicator of relative economic wellbeing than non-equivalised household income.

26 Equivalised household income is derived by calculating an equivalence factor according to an equivalence scale, and then dividing household income by the factor. In this publication the 'modified OECD' equivalence scale is used. The equivalence factor derived using this scale is built up by allocating points to each person in a household. Taking the first adult in the household as having a weight of 1 point, each additional person who is 15 years or older is allocated 0.5 points, and each child under the age of 15 years is allocated 0.3 points. Equivalised gross household income is derived by dividing total gross household income by a factor equal to the sum of the equivalence points allocated to the household members. The equivalised gross household income of a lone person is the same as its unequivalised gross household income. The equivalised gross household income of a household comprising more than one person lies between the total value and the per capita value of its unequivalised gross household income.

Interpretation of results

27 Care has been taken to ensure that the results of this survey are as accurate as possible. All interviews were conducted by trained ABS Interviewers. Extensive reference material was developed for use in the field enumeration and intensive training was provided to interviewers in both classroom and on-the-job environments. There remain, however, other factors which may have affected the reliability of results, and for which no specific adjustments can be made. The following factors should be considered when interpreting these estimates:

  • Information recorded in this survey is essentially 'as reported' by respondents, and hence may differ from information available from other sources or collected using different methodologies. Responses may be affected by imperfect recall or individual interpretation of survey questions.
  • Some respondents may have provided responses that they felt were expected, rather than those that accurately reflected their own situation. Every effort has been made to minimise such bias through the development and use of culturally appropriate survey methodology.
     

28 The Survey of Mental Health and Wellbeing (SMHWB) is the best ABS source of information on the prevalence of mental health conditions in Australians aged 16-85 years. The SMHWB is different from other surveys collecting mental health data because it does not rely on self-reporting. Rather, it uses diagnostic assessment criteria to assess the lifetime, and 12-month prevalence, of selected mental disorders through the measurement of symptoms and their impact on day to day activities. The survey was based on a widely used international survey instrument (World Mental Health Survey Initiative version of the World Health Organization Composite International Diagnostic Interview, version 3.0), but tailored for the Australian context.

29 Other surveys, including the GSS, rely on self-reporting of diagnosed mental health conditions. While not providing a prevalence measure, information obtained from these surveys is valuable for comparing population characteristics of people with/without a mental health condition within the particular survey in which it has been used.

30 The voluntary work estimates for 2014 presented in the survey, exclude those persons who were compelled to do voluntary work because of employment or study commitments, for example, work for the dole. For further information on voluntary work, and for comparisons over time, refer to the publication Voluntary Work, Australia (cat. no. 4441.0).

31 For a number of GSS data items, some respondents were unwilling or unable to provide the required information. No imputation was undertaken for this missing information. Where responses for a particular data item were missing for a person or household they were recorded in a 'not known or not stated' category for that data item. These 'not known or not stated' categories are not shown in the publication tables. However, the person or household has been included in the total for most data items. Below is a table showing the number and proportion of missing values for key GSS data items.

Key GSS data items with a 'not known or not stated' category
Data itenEstimated number of persons ('000)Percentage (%)
Landlord type12.8*0.1
Weekly mortgage payments980.15.3
Weekly rent payments121.80.7
Personal gross weekly income2,313.712.5
Equivalised household gross weekly income4,187.122.7
Principal source of personal income(a)287.81.6
Principal source of household income(a)356.31.9
Whether government support has been main source of income in last 2 years7.1**0.0
Time spent on government support as main source of income in last 2 years95.60.5
Type(s) of cash flow problem(s) (and Number of different types of cash flow problems in last 12 months)322.11.7
Types of dissaving actions taken in last 12 months (and Number of different types of dissaving actions taken in last 12 months)406.02.2
Value of dwelling637.23.4
Equity in dwelling1,293.97.0
Type(s) of selected assets423.92.3
Type of consumer debt406.32.2
Type(s) of personal stressors experienced in last 12 months0.0***0.0

* estimate has a relative standard error of 25% to 50% and should be used with caution
** estimate has a relative standard error greater than 50% and is considered too unreliable for general use
*** Nil or rounded to zero (including null cells)

  1. Also see paragraph 32

32 For persons or households reporting nil or negative total income, or where the income amount was unknown, the principal source of income has been classified as 'undefined'. The principal source of personal income was 'undefined' for an estimated 2.7 million persons (15%). An estimated 345,000 persons lived in households where the principal source of household income was 'undefined' (2%).

Classifications

33 Occupation data were classified according to the Australian ANZSCO - Australian and New Zealand Standard Classification of Occupations, 2013, Version 1.2 (cat. no. 1220.0).

34 Country of birth data were classified according to the Standard Australian Classification of Countries (SACC), 2011 (cat. no. 1269.0).

35 Area data (Capital city, Balance of state/territory; Remoteness areas) are classified according to the Australian Statistical Geography Standard (ASGS).

36 Education data were classified according to the Australian Standard Classification of Education, 2001 (cat. no. 1272.0).

Comparability with 2010 GSS

37 Selected summary results from the 2006 and 2010 GSS are presented in this publication to provide comparisons over time. The statistical significance of differences in estimates between 2010 and 2014 have been investigated. For the 2014 estimates in Table 1 where the difference, when compared to the 2010 rate is statistically significant, a cell comment has been included. While the content and data collection were largely the same in both collections, the sample design and weighting procedures were not. Some differences are noted below.

38 The GSS is designed to collect information for a core set of topics in each cycle, to allow analysis of changes over time, and a cyclical component to collect additional information. Approximately 80% of the content of the 2010 GSS was repeated in the 2014 GSS. Differences in content between the surveys include the cyclical component of the GSS and some new content. A detailed voluntary work module similar to what formed part of the 2006 iteration, was included as part of the cyclical component for the 2014 GSS. This will allow more direct comparison with the 2006 volunteering data. New topics in 2014 included long term health condition, discrimination, visa status, barriers to employment, sexual orientation and parental educational attainment.

39 A full list of the data items from the 2014 GSS are contained in the Data Item List which can be found in the Data downloads section. For published results from the 2010 GSS, refer to General Social Survey: Summary Results, Australia, 2010 (cat. no. 4159.0).

40 Level of highest educational attainment was derived from information on highest year of school completed and level of highest non-school qualification. The derivation process determines which of the 'non-school' or 'school' attainments will be regarded as the highest. Usually the higher ranking attainment is self-evident, but in some cases some secondary education is regarded, for the purposes of obtaining a single measure, as higher than some certificate level attainments. The 2010 GSS treated those respondents who had completed a lower level certificate as having a higher qualification than Year 10. This was different for the 2014 GSS, where Year 10 was treated as having a higher qualification than a lower level certificate.

41 There is a conceptual difference between the 2010 and 2014 GSS in the way that those who had 'No disability or no long term health condition' are derived. In the 2010 GSS, there was no long term health conditions module, so the category 'Has no disability or no long term health conditions' was only derived using the questions in the disability module. In 2014, there was a long term health condition module as well as a disability module, so the appropriate questions across the two modules have been used to derive this category. Conceptually, this means that this particular category for Disability Status should not be compared between the 2010 and 2014 iterations.

42 The Appendix presents comparisons between a number of key GSS data items and similar data items from other ABS sources. Where possible, results from other surveys have been adjusted to the scope and coverage of the GSS (or vice versa). A list of data comparisons can be found in the spreadsheet 'Data Comparability between GSS and Other ABS Sources' in the Data downloads section.

Products and services

43 Below is information describing the range of data to be made available from the 2014 GSS, both in published form and on request. Products available on the ABS web site are indicated accordingly.

General Social Survey: Summary results, Australia, 2014 datacubes

44 The tables released in this product are in spreadsheet format and are available in the Data downloads section of this publication. Estimates, proportions and the related Relative Standard Errors (RSEs) are presented for each table.

General Social Survey: User guide 2014

45 The GSS User Guide will be released in conjunction with the Confidentialised Unit Record File (CURF). It will provide detailed information about the survey content, methodology and data interpretation. It is expected that the User Guide will be available free-of-charge on the ABS web site in September 2015 (cat. no. 4159.0.55.002).

Microdata

46 It is expected that a Table Builder and an expanded confidentialised unit record file (CURF) will be produced from the GSS, subject to the approval of the Australian Statistician. The expanded CURF will be available via Remote Access Data Laboratory (RADL) and ABS Data Laboratory (ABSDL), and the Table Builder will be accessible via the ABS website, using a secure log-on portal.

47 Special tabulations of GSS data are available on request. Subject to confidentiality and sampling variability constraints, tabulations can be produced from the survey incorporating data items, populations and geographic areas selected to meet individual requirements. These can be provided in printed or electronic form. All enquiries should be made to the National Information and Referral Service on 1300 135 070.

Acknowledgements

48 ABS publications draw extensively on information provided freely by individuals, businesses, government and other organisations. Their continued cooperation is very much appreciated; without it, the wide range of statistics published by the ABS would not be available. Information received by the ABS is treated in strict confidence as required by the Census and Statistics Act 1905.

Appendix - data comparability with other ABS sources

Show all

Technical note - data quality

Reliability of the estimates

1 The estimates in this publication are based on information obtained from a sample survey. Any data collection may encounter factors, known as non-sampling error, which can impact on the reliability of the resulting statistics. In addition, the reliability of estimates based on sample surveys are also subject to sampling variability. That is, the estimates may differ from those that would have been produced had all persons in the population been included in the survey.

Non-sampling error

2 Non-sampling error may occur in any collection, whether it is based on a sample or a full count such as a census. Sources of non-sampling error include non-response, errors in reporting by respondents or recording of answers by interviewers and errors in coding and processing data. Every effort is made to reduce non-sampling error by careful design and testing of questionnaires, training and supervision of interviewers, and extensive editing and quality control procedures at all stages of data processing.

Sampling error

3 One measure of the likely difference is given by the standard error (SE), which indicates the extent to which an estimate might have varied by chance because only a sample of persons was included. There are about two chances in three (67%) that a sample estimate will differ by less than one SE from the number that would have been obtained if all persons had been surveyed, and about 19 chances in 20 (95%) that the difference will be less than two SEs.

4 Another measure of the likely difference is the relative standard error (RSE), which is obtained by expressing the SE as a percentage of the estimate.

\(\large{R S E \%=\left(\frac{S E}{\text {estimate}}\right) \times 100}\)

5 RSEs for count estimates have been calculated using the Jackknife method of variance estimation. This involves the calculation of 60 'replicate' estimates based on 60 different sub samples of the obtained sample. The variability of estimates obtained from these sub samples is used to estimate the sample variability surrounding the count estimate.

6 The Excel spreadsheets in the Data downloads section contain all the tables produced for this release and the calculated RSEs for each of the estimates.

7 Only estimates (numbers or percentages) with RSEs less than 25% are considered sufficiently reliable for most analytical purposes. However, estimates with larger RSEs have been included. Estimates with an RSE in the range 25% to 50% should be used with caution while estimates with RSEs greater than 50% are considered too unreliable for general use. All cells in the Excel spreadsheets with RSEs greater than 25% contain a comment indicating the size of the RSE. These cells can be identified by a red indicator in the corner of the cell. The comment appears when the mouse pointer hovers over the cell.

Calculation of standard error

8 Standard errors can be calculated using the estimates (counts or percentages) and the corresponding RSEs. See What is a Standard Error and Relative Standard Error, Reliability of estimates for Labour Force data for more details.

Proportions and percentages

9 Proportions and percentages formed from the ratio of two estimates are also subject to sampling errors. The size of the error depends on the accuracy of both the numerator and the denominator. A formula to approximate the RSE of a proportion is given below. This formula is only valid when x is a subset of y:

\(R S E\left(\frac{x}{y}\right) \approx \sqrt{[R S E(x)]^{2}-[R S E(y)]^{2}}\)

Differences

10 The difference between two survey estimates (counts or percentages) can also be calculated from published estimates. Such an estimate is also subject to sampling error. The sampling error of the difference between two estimates depends on their SEs and the relationship (correlation) between them. An approximate SE of the difference between two estimates (x-y) may be calculated by the following formula:

\(S E(x-y) \approx \sqrt{[S E(x)]^{2}+[S E(y)]^{2}}\)

11 While this formula will only be exact for differences between separate and uncorrelated characteristics or sub populations, it provides a good approximation for the differences likely to be of interest in this publication.

Significance testing

12 A statistical significance test for a comparison between estimates can be performed to determine whether it is likely that there is a difference between the corresponding population characteristics. The standard error of the difference between two corresponding estimates (x and y) can be calculated using the formula shown above in the Differences section. This standard error is then used to calculate the following test statistic:

\(\large{\frac{|x-y|}{S E(x-y)}}\)

13 If the value of this test statistic is greater than 1.96 then there is evidence, with a 95% level of confidence, of a statistically significant difference in the two populations with respect to that characteristic. Otherwise, it cannot be stated with confidence that there is a real difference between the populations with respect to that characteristic.

Glossary

Show all

Quality declaration

Institutional environment

Relevance

Timeliness

Accuracy

Coherence

Interpretability

Accessibility

Abbreviations

Show all

Back to top of the page