1 This publication presents the results of the 2005 Personal Safety Survey (PSS) which was conducted by the Australian Bureau of Statistics (ABS) throughout Australia from August to December 2005.
2 Information was collected from persons aged 18 years and over about their safety at home and in the community. In particular, information was collected about experiences of physical and sexual violence, the nature and extent of the violence against women and men, actions taken after experiencing violence and the effect on their lives. Additional information was collected about incidents of abuse, stalking and other forms of harassment.
SCOPE OF THE SURVEY
3 Personal face to face interviews were conducted with one randomly selected person aged 18 years or over who was a usual resident of the selected household. Both urban and rural areas in all states and territories were included, but very remote areas of Australia were excluded. The following groups were also excluded from the survey:
- certain diplomatic personnel of overseas governments, customarily excluded from the Population Census and estimated population figures
- overseas residents in Australia
- members of non-Australian defence forces (and their dependents) stationed in Australia
- residents of non-private dwellings, such as hospitals, retirement villages, refuges etc.
4 Dwellings were selected at random using a multistage area sample of private dwellings. The initial sample selected for the survey consisted of approximately 27,000 dwellings. This was reduced to a sample of approximately 22,000 after sample loss (e.g. households selected in the survey which had no residents in scope of the survey, vacant or derelict buildings, buildings under construction). Of those remaining dwellings 76.2% were fully or adequately responding, yielding a total sample for the survey of 11,800 females and 4,500 males.
5 The PSS was conducted in both urban and rural areas in all states and territories, but excluded approximately 120,000 persons living in very remote areas of Australia who would otherwise have been within the scope of the survey. The exclusion of these persons would have only a minor impact on any aggregate estimates that are produced for individual states and territories, except for the Northern Territory where such persons account for around 23% of the population.
6 The PSS survey design required special procedures for sample selection in order to achieve the targeted numbers of females and males. Also, in the non-metropolitan areas, the sample design incorporated selection of dwellings close to interviewers with a higher probability. Further details of these design elements may be found in Personal Safety Survey, Australia: User Guide (cat. no. 4906.0.55.003).
WEIGHTING, BENCH MARKING AND ESTIMATION
7 Weighting is a process of adjusting results from a sample survey to infer results for the total population. To do this, a weight is allocated to each sample unit. The weight is a value which indicates how many population units are represented by the sample unit.
8 The first step in calculating weights for each person was to determine an initial household weight, equal to the inverse of the probability of the household being selected in the survey. For example, if the probability of a household being selected in the survey was 1 in 600, then the household would have an initial weight of 600 (that is, they represent 600 others). An adjustment was then made to the household weights for household composition. Initial person weights were derived from the adjusted household weights according to the number of in-scope males or females in the household.
9 The person weights were then calibrated to align with independent estimates of the population of interest, referred to as 'benchmarks', in designated categories of sex by age by area of usual residence categories. Weights calibrated against population benchmarks help to compensate for over or under-enumeration of particular categories of persons and ensure that the survey estimates conform to the independently estimated distribution of the population by age, sex and area of usual residence, rather than to the distribution within the sample itself.
10 Estimates obtained from the survey were derived using a complex ratio estimation procedure. This procedure ensures that survey estimates conform to an independently estimated distribution of the total population by age and area (rather than to the age-area distribution within the sample itself). The survey was conducted during August to December 2005, and estimates were made to conform to the population distribution during that period.
11 In addition to standard ABS training in the content and procedures for the survey the interviewers received sensitivity and awareness training to increase their understanding of and ability to deal with issues related to violence against women and men.
12 A specific requirement of the survey was that all interviews had to be conducted alone. This ensured the complete confidentiality of any information collected and the security of both the respondent and the interviewer where the respondent may have been living in the same household as the perpetrator. If preferred by the respondent, the interview could be conducted over the telephone.
13 Respondents were given the opportunity to have the interview conducted by a male interviewer. However, all interviews were conducted by female interviewers.
14 More detailed information about the methods used to conduct the survey are found in Personal Safety Survey, Australia: User Guide (cat. no. 4906.0.55.003).
RELIABILITY OF ESTIMATES
15 The estimates provided in this publication are subject to sampling and non-sampling errors.
16 Sampling error is the difference between the published estimates and the corresponding figures that would have been obtained from a collection based on the whole population, using the same questionnaires and procedures. A measure of the sampling error for a given estimate is provided by the standard error expressed as a percentage of the estimate (relative standard error). For more information refer to the Technical Notes (paragraphs 1-4). In this publication, estimates with a high relative standard error of 25% to 50% are preceded by an asterisk (e.g. *3.4) to indicate the estimate should be used with caution. Estimates with a relative standard over 50% are indicated by a double asterisk (**0.6) and are considered too unreliable for most purposes.
17 Non-sampling errors can occur whether the estimates are derived from a sample or from a census. The major sources of non-sampling errors are:
18 Non-sampling errors are difficult to measure in any collection. However, every effort was made to minimise these errors. In particular, the effect of the reporting and processing errors described above were minimised by careful questionnaire design, extensive training of interviewers and extensive editing and quality control checking at all stages of data processing.
- inability to obtain comprehensive data from some women and men in the sample. These errors arise because of differences which exist between the characteristics of respondents and non-respondents
- errors in reporting by either the respondent or the interviewer, arising from inappropriate wording of questions, misunderstanding of the information required, inability or unwillingness to provide accurate information and mistakes in answers to questions
- errors arising during processing of the survey data, such as mistakes in coding and data recording.
19 More detailed information about issues to consider when interpreting the survey results are contained in 2005, Personal Safety Survey, Australia: User Guide (cat. no. 4906.0.55.003).
20 The difference in results from the 1996 WSS and the 2005 PSS have been subject to testing to determine whether the changes are statistically significant - that is, to determine whether the differences we observe in sample estimates over time indicate real differences. In tables 5, 6, 7 and 8, and text that compare the two surveys, all data has been significance tested and all changes over time presented are significant. For other comparisons between data from the 1996 WSS and the 2005 PSS, it is recommended that significance testing is undertaken to determine whether there is a real difference between the corresponding population characteristics. Refer to the Technical Note (paragraph 12) for details on significance testing.
21 Other ABS publications on related topics which may be of interest include:
22 All current publications produced by the ABS are listed in the Catalogue of Publications and Products (cat. no. 1101.0). The ABS also issues a Release Advice (cat. no. 1105.0) which lists products released by all ABS offices on the day of the issue of the Release Advice and those expected to be released on the following four working days. Copies are available free of charge on Tuesdays and Fridays over the counter from ABS bookshops or by subscription. A daily Release Advice is also available from the ABS statsite on the Internet <www.abs.gov.au>. The Catalogue and Release Advice are available from any ABS office.
Crime and Safety, Australia, 2005, cat. no. 4509.0
General Social Survey: Summary Results, Australia, 2002, cat. no. 4159.0
Information Paper: Measuring Crime Victimisation, Australia: The impact of different collection methodologies, 2002, cat. no. 4522.0.55.001
Information paper: National Information Development Plan for Crime and Justice Statistics, 2005, cat. no. 4520.0
Recorded Crime - Victims. Australia, 2004, cat. no. 4510.0
Sexual Assault in Australia: A Statistical Overview, 2004, cat. no. 4523.0
Women's Safety, Australia, 1996, cat. no. 4128.0
23 Results from other surveys which may also be of interest include: International Crime Victims Survey (ICVS), International Violence Against Women Survey (IVAWS) conducted by the Australian Institute of Criminology (AIC).
24 This publication does not include all the information available from the survey. Additional tables, providing more detail, or data items not included in this publication are available on request. The Glossary provides definitions of data items and terms used in the PSS. Personal Safety Survey, Australia: User Guide (cat. no. 4906.0.55.003), provides a comprehensive list of data items available from the survey. Users should be aware that as the level of disaggregation increases, the number of respondents contributing to data cells decreases, and so sample error increases. Further information about the survey and associated products can be obtained from the the contact officer listed on the front of this publiction.