Personal Safety, Australia methodology

1 The statistics presented in this release were compiled from data collected in the Australian Bureau of Statistics (ABS) 2016 Personal Safety Survey (PSS), conducted from November 2016 to June 2017.

2 The survey collected information from men and women aged 18 years and over about the nature and extent of violence experienced since the age of 15. It also collected detailed information about men's and women's experience of current and previous partner violence and emotional abuse, experiences of stalking since the age of 15, sexual and physical abuse before the age of 15, witnessing of violence between a parent and their partner before the age of 15, lifetime experience of sexual harassment, and general feelings of safety.

3 The statistics presented in this release, refer to the Data downloads which can be accessed in the Downloads section and are indicative of the extensive range of data available from the survey and demonstrate the analytical potential of the survey results.

4 Full details about all the data collected in the 2016 PSS are provided in the Data Item List. This and other detailed information on how to maximise the use of the extensive range of data are available in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003). Additional information may be made available by request, on a fee for service basis, through the ABS Information Consultancy, or via TableBuilder or Detailed Microdata products which are expected to be released in the first quarter of 2018.

5 This is the third time the PSS has been conducted. The PSS was last run in 2012, and prior to that in 2005. The PSS is based on the design of the Women's Safety Survey (WSS) (cat. no. 4128.0) which was conducted in 1996, and has been adapted to include men's experience of violence. This release includes some data comparisons with previous iterations where appropriate.

6 The PSS meets the need for updated information on the nature and extent of violence experienced by men and women in Australia and other related information regarding people's safety at home and in the community.

7 The need for data on the prevalence of violence and sexual assault is discussed in the National Plan to Reduce Violence against Women and their Children 2010-2022, and in the following ABS Information Papers:

• Defining the data challenge for Family, Domestic and Sexual Violence (cat. no. 4529.0)
• Directory of Family and Domestic Violence Statistics (cat. no. 4533.0)
• Bridging the data gaps for family, domestic and sexual violence (cat. no. 4529.0.00.002)
   

8 ABS acknowledges the support and input of the Department of Social Services (DSS) which, under the National Plan to Reduce Violence Against Women and their Children 2010-2022, provided funding for the 2016 PSS. A Survey Advisory Group, comprising key government and non-government bodies, provided the ABS with advice on the information to be collected and on some aspects of survey methodology. Members of this group included representatives from State and Commonwealth Government departments, crime research agencies, service providers and relevant academics.

9 The scope of the 2016 PSS was persons aged 18 years and over in private dwellings across Australia (excluding very remote areas). Interviews were conducted with one randomly selected person aged 18 years or over who was a usual resident of the selected household.

10 Both urban and rural areas in all states and territories were included in the survey, except for very remote areas of Australia. The following groups were excluded from the scope of the survey:

• visitors at a dwelling whose usual place of residence is Australia
• overseas visitors intending to stay in Australia for less than 12 months
• non-Australian diplomats, non-Australia diplomatic staff and non-Australian members of their household
• members of non-Australian defence forces stationed in Australia and their dependants
• people who usually reside in non-private dwellings, and
• households where all residents are aged less than 18 years.
   

11 The 2016 PSS was designed to produce reliable estimates for selected key estimates of interest. Each of these key estimates were then required to be disaggregated for:

• women: for each state and territory (and at the national level)
• men: at the national level. While the survey was not designed to provide state/territory level data for men, estimates of acceptable quality are able to be produced for some of the larger states.
   

12 The sample for women was allocated roughly equally across each state and territory to provide sufficiently reliable state and territory and national level estimates for women. The sample for men was allocated to states and territories roughly in proportion to their respective population size to provide sufficiently reliable national level estimates for men. In order to target the differential numbers of male and female sample, dwellings were pre-assigned for either male selection (where an interview with a male aged 18 years and over was required) or female selection (where an interview with a female aged 18 years and over was required). One in-scope person of the pre-assigned gender was then randomly selected from each dwelling. Where the household did not contain an in-scope resident of the pre-assigned gender, an in scope resident of the alternate gender was randomly selected. For further information refer to the Survey Development and Data Collection page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

13 Response rates to the survey were expected to be impacted by a number of operational factors that were designed to help ensure the safety of respondents, the safety of interviewers and to help ensure data integrity. These included:

• the part voluntary nature of the survey
• requirement for all interviews to be conducted in a private interview setting
• proxy interviews were not conducted for the voluntary component (therefore people requiring a proxy are not included in the final data), and
• the overall sensitive nature of the survey content.
   

14 There were 36,495 private dwellings approached for the survey, comprising 7,074 pre-assigned male households and 29,421 pre-assigned female households.

15 After removing households where residents were out of scope of the survey, and where dwelling proved to be vacant, under construction or derelict, a final sample of 30,933 eligible dwellings were identified.

16 A final response rate of 68.7% was achieved, with 21,242 persons completing the questionnaire nationally. The response comprised 5,653 fully responding males and 15,589 fully responding females.

17 For further details on the response rates, refer to the Response Rates page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

18 Personal face to face interviews were conducted with one randomly selected person aged 18 years and over who was a usual resident of the selected household. Interviews were conducted from November 2016 to June 2017. On average contact time with fully responding households was 33 minutes.

19 The 2016 PSS was conducted under the authority of the Census and Statistics Act 1905. This ensures that the ABS has the authority to ask questions and that the confidentiality provisions of the Act will be applied, as in all ABS surveys. However, because of the potential sensitivities of parts of this survey, the compliance provisions of the Act were not fully applied and the survey was conducted on a part voluntary basis.

20 Due to the sensitive nature of the information being collected, as with previous cycles, special procedures were used to ensure the safety of those participating and the reliability of the data provided.

21 Information was collected by specially trained ABS interviewers. The training program included sessions to familiarise the interviewers with:

• the concepts addressed in the survey (definitions)
• the specialised survey procedures developed for the survey (including sensitive approach methods to maximise response)
• the Computer Assisted Interview (CAI) instrument (via Computer Assisted Personal Interview (CAPI) and Computer Assisted Self Interview (CASI)), and
• administrative aspects of the survey.
   

22 In addition to the standard ABS training provided to ABS interviewers regarding the survey content and field procedures, interviewers also received tailored sensitivity and awareness training, designed to increase their knowledge and understanding of what happens when a person experiences violence. The ABS utilised external consultants, specialised in this field to provide this component of the interviewer training.

23 To help ensure respondent comfort and well-being, as well as encouraging participation, the ABS used female interviewers for the PSS. It was considered that men and women would be more likely to feel comfortable revealing sensitive information about their possible experiences of violence to a woman. This was based on collective advice from experts in the field during the survey development, was in line with the successful procedures followed for the 2005 and 2012 PSS, and was also supported by the 2016 PSS Survey Advisory Group. To cater for instances where this might not be the case, the ABS also trained a small number of male interviewers, in case a respondent preferred that their interview be conducted by a male.

24 Prior to enumeration, all selected households were sent out pre-approach material by mail that consisted of the following:

• a registration letter and leaflet, sent to the dwelling 21 days prior to enumeration requesting household to register contact details, and
• a reminder letter, sent 16 days prior to enumeration.
   

The materials sent out were kept deliberately vague regarding the information that would be collected and assured respondents of the confidentiality of data collected. The letters did not detail the sensitive information to be collected.

25 If households registered contact details for the survey, the interviewer called first to collect household details to determine who the selected person was so that arrangements to speak with them could be made prior to attending the house. If household contact details weren't registered, the interviewer approached the house in person. A series of screening questions were asked of the person initially answering the door, to determine the number of usual male/female residents aged 18 years and over.

26 Selected respondents were first advised of the general nature of the survey. During the interview, less sensitive questions were asked first, such as their demographic details and general feelings of safety questions. This allowed people to develop a certain level of rapport with the interviewer and familiarised them with some survey content.

27 Once the questions regarding a person's experience of violence were reached, respondents were informed of the sensitive nature of the upcoming questions and their permission to continue with the interview was sought (referred to as the Opt-out point). At this point the respondent was also advised that the interview would continue as a Computer Assisted Self-Enumeration Interview (CASI), that is, the respondent could complete the interview themselves using the interviewer's laptop. If the respondent identified that they were not comfortable to continue in this interview mode, the interviewer could offer to continue conducting the interview (referred to as a Computer Assisted Personal Interview (CAPI)). In these situations, it was a specific requirement that all CAPIs for the sensitive topics be conducted alone (including no children) in a private setting. Interviewers were also advised that if the respondent chose to complete the voluntary component as a CASI, they should ensure that other people could not see the screen or respondent reactions, or hear any queries the respondent may ask about the questions. If they could, then the interviewer was advised to follow the same procedures as a CAPI interview.

28 For the 2016 PSS, proxy interviews, if required for translation or due to the respondent being incapable of responding for themselves as a result of a significant medical reason, were used to complete the compulsory part of the survey. For these interviews, the sensitive voluntary component of the survey was not mentioned and questions on these topics were not asked. The use of proxy interviews for the compulsory part of the survey provided information on the possible under representation in the survey of particular types of respondents, such as those from a non-English speaking background or with a profound or severe communication disability. For a detailed definition of proxy, refer to the Glossary.

29 To cater for instances where a respondent did not speak English, a small number of interviewers with foreign language skills were trained to conduct PSS interviews.

30 For further information on data collection and survey procedures, refer to the Survey Development and Data Collection page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

31 Weighting is the process of adjusting results from a sample survey to infer results for the total in-scope population. To do this, a 'weight' is allocated to each sample unit corresponding to the level at which population statistics are produced. For the 2016 PSS, this is at a person level. The weight can be considered an indication of how many population units are represented by the sample unit.

32 The first step in calculating weights for each person was to assign an initial weight, which was 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 one in 600, then the person would have an initial weight of 600 (that is, they represent 600 people).

33 Using information based on observations by interviewers at the dwelling, as well as additional information collected from non-fully responding respondents as part of the compulsory component of the survey, analysis was undertaken to ascertain whether there were any particular categories of persons that were over or under-represented in the sample. This over or under-representation in the sample can be corrected using a non-response adjustment and/or through calibrating the weights to population benchmarks. Only calibrating the weights to population benchmarks was adopted for the 2016 PSS.

34 Benchmarks are independent estimates of the size of the population of interest. Weights are calibrated against independent population benchmarks to ensure that the survey estimates conform to the independently estimated distribution of the population, with respect to the benchmark categories, rather than to the distribution within the responding sample itself. The 2016 PSS survey estimates were benchmarked to the estimated resident Australian population aged 18 years and over who were living in private dwellings (excluding very remote areas of Australia) as at February 2017, simultaneously using the following benchmark categories:

Number of persons by -

• State or territory by capital city/balance of state by age groups by sex
• State or territory by Social marital status (Married in registered or de facto marriage and Not married) by sex
• State or territory by broad Country of birth (Australia, Main English Speaking categories and Other) by sex
• State or territory by Labour force status (Full Time Employed, Part Time Employed, Unemployed, or Not In the Labour Force) by sex, and
• Age group (slightly more detailed) by sex.
   

35 Estimation is a technique used to produce information about a population of interest, based on a sample of units (i.e. persons) from the population. Each record in the 2016 PSS has a person weight. Information for sampled persons is multiplied by the weights to produce estimates for the whole population.

36 For further information on weighting, benchmarking and estimation, refer to the Methodology page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003)

37 A key objective of the 2016 PSS was to collect information about the prevalence of men's and women's experience of violence since the age of 15. This includes their experience of physical assault, sexual assault, physical threat and sexual threat by male and female perpetrators (for six key perpetrator types: current partner, previous partner, boyfriend/girlfriend or date, ex-boyfriend/ex-girlfriend, other known person, and stranger). This provides information on the prevalence of the different types of violence by different perpetrator types.

38 Where a person had experienced any of these types of violence, more detailed information was then collected for their most recent incident of each of the eight types of violence: physical assault, sexual assault, physical threat and sexual threat by a male and by a female perpetrator. This information is used to understand what happens when a person experiences violence by a male or female perpetrator and how this differs depending on the different types of violence.

39 Where someone had experienced violence by a current partner and/or previous partner they were asked further questions about what happened during the relationship. This information was collected separately for current partner violence and previous partner violence: if someone had experienced violence by more than one previous partner, the information was collected about their most recently violent previous partner only.

40 Other topics collected include experiences of stalking since the age of 15, abuse before the age of 15, witness violence towards a parent and their partner before the age of 15, partner emotional abuse, lifetime experience of sexual harassment and general feelings of safety.

41 Care has been taken to ensure that results in the 2016 PSS are as accurate as possible. This includes thorough design and testing of the questionnaire, interviews being conducted by trained ABS interviewers, and quality control procedures throughout data collection, processing and output. For information on detailed interpretation of results refer to the relevant topic pages in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

42 It is possible that people have experienced multiple incidents of violence. Where a person has experienced more than one type of violence, they are counted separately for each type of violence they experience but are only counted once in the aggregated totals. Components therefore may not add to the totals. For example if a person had experienced an incident of physical assault by a stranger and an incident of physical assault by their current partner, they would be counted against each type of violence by type of perpetrator (i.e. physical assault by a stranger and physical assault by a current partner) but they would only be counted once in the total for those who had experienced physical assault.

43 It is also possible that a single incident of violence may involve more than one of the different types of violence. In the PSS, a single incident of violence is only counted once. Where an incident involves both sexual and physical assault, it is counted as a sexual assault. For example, if a person is physically assaulted during or as part of a sexual assault, this would be counted once only as a sexual assault. Where an incident involves a person being both threatened with assault and assaulted, it is counted as an assault. For example, if in a single incident a perpetrator threatens to sexually assault a person and then sexually assaults them, this would be counted only once in the survey as a sexual assault. The same applies for incidents where a person is both threatened with physical assault and physically assaulted.

44 For detailed descriptions and definitions of violence, refer to the Glossary.

45 The characteristics and actions taken following an incident of violence differ depending on the type of violence a person experienced and the gender of the perpetrator. Due to constraints on the length of an interview and the load placed on respondents, it was not possible to collect detailed information about each incident of violence a person had ever experienced. Instead, detailed information was collected about their most recent incident for each of the eight different types of violence. A 'most recent' incident method was used to select a sample of incidents. If the most recent incident occurred more than 10 years ago, detailed information was not collected due to difficulties associated with recalling the incident and to reduce respondent burden. For further information refer to the Violence - Most recent incident page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

46 People who had experienced violence within the last 10 years were asked to provide more detailed information about their most recent incident including: what happened during the incident; the actions taken following the incident; and the impact of the incident. This provides information for each of the eight different types of violence a person could experience:

• Sexual assault by a male perpetrator
• Sexual assault by a female perpetrator
• Sexual threat by a male perpetrator
• Sexual threat by a female perpetrator
• Physical assault by a male perpetrator
• Physical assault by a female perpetrator
• Physical threat by a male perpetrator
• Physical threat by a female perpetrator
   

47 Most recent incident data information is able to be used to analyse the different types of violence experienced by men and women to assess:

• Whether there are differences in what happens when different types of violence are experienced, and
• Whether there are differences between what happens when a woman experiences violence, and when a man experiences violence.
   

48 The information provided above can be used to produce a range of prevalence estimates for men's and women's experiences of violence, according to the type of violence, the type and sex of the perpetrator, and time frame. Prevalence refers to the number and proportion (rate) of persons in a given population that have experienced any type of violence within a specified time frame - usually in the last 12 months and since the age of 15. Prevalence rates are calculated by dividing the number of men/women/persons that have experienced the type of violence since the age of 15 by the total number of persons aged 18 years and over within that same population. For further information refer to the Violence - Prevalence page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

49 The characteristics of the different types of violence are not able to be added to produce a total for characteristics of "violence". Conceptually it is invalid to add together data about the characteristics for the different types of violence, as actions a person may take could differ depending on the type of violence experienced. For example, if a person had contacted the police about their most recent incident of physical assault by a male but had not contacted police about their most recent incident of physical assault by a female, it is impossible to calculate an estimate of whether or not this person has contacted the police about "violence" - they both have and haven't. To add together data about characteristics of the different types of violence would also double count all persons who have experienced more than one type of violence.

50 The definition of child abuse can vary across the different sectors of government, criminal justice systems, service providers and research organisations, depending on the perspective and interests of the organisation that have created it.

51 Sexual abuse is defined as any act involving a child (under the age of 15 years) in sexual activity beyond their understanding or contrary to currently accepted community standards. This excludes emotional abuse and sexual abuse under the age of 18.

52 Physical abuse is defined as any deliberate physical injury (including bruises) inflicted upon a child (under the age of 15 years) by an adult. This excludes discipline that accidentally resulted in injury, emotional abuse, and physical abuse by someone under the age of 18.

53 The 2016 PSS collected information about a respondent’s experience of sexual and physical abuse before the age of 15 years by any adult (male or female). Respondents were asked if they were sexually and/or physically abused by an adult (aged 18 years or over) before the age of 15. The same set of questions was repeated twice, for sexual abuse and physical abuse separately. Due to the sensitive nature of the module, respondents had the option of declining to answer these questions. If a respondent answered that they had experienced sexual or physical abuse before the age of 15, they were asked to identify all of the adult perpetrator types that abused them.

54 Information about the characteristics of the first incident of abuse was collected separately for sexual abuse and physical abuse. The Abuse before the age of 15 module was primarily designed to be used in conjunction with information collected in other parts of the survey in order to analyse the relationship between experiences of child abuse before the age of 15 and later experiences of violence as an adult from the age of 15. For further information refer to the Abuse before the age of 15 page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

55 In the context of this module, violence refers to physical assault only and only encompasses violence witnessed between a parent and their partner. The 2016 PSS collected information about whether the respondent, before the age of 15, ever saw or heard violence being directed at one parent by another. The definition of violence used was the same as used to collect physical assault data in the Violence since the age of 15 topic. Mother includes step mothers and female guardians or caregivers. Partner includes the respondent’s father/stepfather, and the mother’s boyfriend or same-sex partner. Father includes step fathers and male guardians or caregivers. Partner includes the respondent’s mother/stepmother, and the father’s girlfriend or same-sex partner.

56 The questions about witnessing violence before the age of 15 were asked separately of the respondent for witnessing violence against their mother by a partner, and witnessing violence against their father by a partner. Respondents that reported having seen or heard any of the above being done to their mother and/or father were then asked how many times they saw or heard these things being done - 'once or twice' or 'more than twice'.

57 The witness violence before the age of 15 module was primarily designed to be used in conjunction with information collected in other parts of the survey to analyse the relationship between seeing and hearing violence as a child towards a parental figure and later experiences of violence as an adult from the age of 15. For further information refer to the Witness violence before the age of 15 page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

58 Partner violence refers to any incident, reported in the Violence since the age of 15 module, of sexual assault, sexual threat, physical assault or physical threat by a current partner they were living with at the time of the survey and/or a previous partner they had lived with. Partner violence does not include violence by a boyfriend/girlfriend or date, which refers to a person that the respondent dated, or was intimately involved with, but did not live with. For detailed descriptions and definitions, refer to the Glossary.

59 If a respondent had identified more than one violent previous partner in the Violence since the age of 15 module, they were asked to focus on their most recently violent previous partner in the Partner violence module.

60 The Partner violence module is designed to capture information about the nature and impact of the violence throughout the duration of the relationship with the current partner and/or most recently violent previous partner. Partner violence data can be used to examine:

• the characteristics of the violence experienced, such as how often violence was experienced
• support-seeking behaviours, such as whether advice or support was sought and from whom
• police involvement, such as whether the police were contacted, and other legal action including whether the partner was charged, whether they went to court, and whether a restraining order was issued
• the impact of the violence on the respondent, including whether they experienced anxiety or fear as a result of the violence, changes to their usual routine, and whether they took time off work, and
• separations from their violent partner as a result of the violence, including whether they ever temporarily separated, reasons for separation, places stayed during temporary separations, whether left property or assets behind, and reasons for returning to the violent partner.
   

61 Partner violence data collected in this module cannot be broken down by the type of violence experienced (sexual/physical assault/threat), only by the type of perpetrator (current or previous). Components for current partner and previous partner violence are not able to be added together to produce data for a 'total partner' aggregate as it would lead to double counting of all persons who have experienced violence by both a current and a previous partner, and does not account for where people had experienced violence by more than one previous partner. For further information refer to the Partner violence page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

62 Emotional abuse occurs when a person is subjected to certain behaviours or actions that are aimed at preventing or controlling their behaviour, causing them emotional harm or fear. These behaviours are characterised in nature by their intent to manipulate, control, isolate or intimidate the person they are aimed at. They are generally repeated behaviours and include psychological, social, economic and verbal abuse. For a detailed definition of emotional abuse, refer to the Glossary.

63 The 2016 PSS collected information about a respondent's experience of emotional abuse since the age of 15, by a current partner they were living with at the time of the survey and/or a previous partner that they had lived with. Where a person had experienced emotional abuse by more than one previous partner, they were asked to focus on the most recently emotionally abusive previous partner when answering the more detailed questions about previous partner emotional abuse. This may or may not have been the same previous partner that was most recently violent, if the respondent had also experienced previous partner violence. In other words, the most recently violent previous partner and most recently emotionally abusive previous partner may be the same or different. Emotional abuse by a previous partner includes abuse that occurred after the relationship ended. For definitions of current partner and previous partner, refer to the Glossary.

64 Partner emotional abuse data can be used to examine:

• the prevalence of partner emotional abuse, and
• the characteristics of emotional abuse by a current and previous partner, such as the types of emotionally abusive behaviours experienced, how often the emotional abuse was experienced, and whether the anxiety or fear was experienced as a result.
   

65 Components for current partner and previous partner emotional abuse are not able to be added together to produce data for a 'total emotional abuse' aggregate as it would lead to double counting of all persons who have experienced emotional abuse by both a current and a previous partner. For further information refer to the Partner emotional abuse page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

66 The 2016 PSS collected information about a respondent's experiences of stalking since the age of 15. Persons were asked if they had experienced stalking by a man and by a woman separately. Stalking was considered to have occurred if a person has experienced:

• any unwanted contact or attention on more than one occasion that could have caused fear or distress, or
• multiple types of unwanted contact or behaviour that could have caused fear or distress.
   

For a detailed definition of stalking, refer to the Glossary.

67 As soon as stalking behaviour had been identified, the episode was the focus of the remainder of the questions which the PSS defines as the most recent stalking episode as the stalking behaviours were likely to have occurred over a protracted period of time. Information about the types of stalking behaviours experienced in the most recent episode, the relationship to the perpetrator, and when the episode of stalking stopped was collected for the most recent episode of stalking by a man and by a woman since the age of 15. If the most recent episode of stalking occurred in the last 20 years, further information about the episode was collected. For further information refer to the Stalking page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

68 Stalking prevalence data is available on the person level as aggregated data items (persons that have experienced stalking by both a man and a woman are only counted once in the aggregated data item 'Whether experienced stalking since age 15'). Stalking prevalence data can be used to examine:

• the estimated number and proportion (rate) of persons that have experienced stalking by a man and/or woman during the last 12 months and since the age of 15, and
• differences in the stalking prevalence rate between the male and female population.
   

69 Most recent episode data can be used to examine:

• differences between men's and women's experiences of stalking, including stalking behaviours experienced, impacts, actions, and outcomes, and
• differences between male perpetrated stalking and female perpetrated stalking, including stalking behaviours experienced, impacts, actions, and outcomes.
   

70 The scope, content and data collection for the 2016 PSS was largely the same as the 2012 survey, with a few key changes:

• Sample size – The sample size for 2016 was significantly larger due to improvements in response rates and changes to sample design.
• Sample design – In 2016, pre-assigned genders selections for households were able to be ‘flipped’ to the alternate gender if no-one aged 18 years or over in the household was of the pre-assigned gender. This is consistent with the approach taken in the 2005 PSS.
• Collection mode – The 2016 PSS introduced the Computer Assisted Self Interview (CASI), which gave respondents the option to complete the sensitive (voluntary) topics themselves using the interviewer laptop.
• Compulsion – In 2016, the PSS was part compulsory, for the collection of demographic and other general non-sensitive topics.
• Content – some changes were made to definitions to assist with respondent understanding as well as the addition of some new content or concepts (for example additional technologically focused behaviours were added to the sexual harassment, stalking and emotional abuse topics).
   

71 Selected summary results from the 1996 Women's Safety Survey, and the 2005, 2012 and 2016 PSS are presented in this publication to provide comparisons over time - refer to Tables 2, 8 and 39. The statistical significance of differences in estimates between 2012 and 2016 has been investigated and results that are statistically significant are indicated in the tables.

72 For further information on 2016 PSS procedures, content changes, and comparability with previous iterations of the PSS, refer to the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

73 The ABS collects and publishes data relating to crime and safety from different sources, for example the Crime Victimisation Survey, Australia and the General Social Survey, Australia and administrative data from police agencies. Comparisons of PSS data with data from other sources cannot be readily made because of differences in data collection methods and the concepts and definitions used to measure violence. For example, survey mode may influence differences (face-to-face versus telephone interviewing), context effects (preceding questions influence responses to subsequent questions), differences in question wording and the length and timing of data collection.

74 Further information on crime data measurement issues is available in the information paper: Measuring Victims of Crime: A Guide to Using Administrative and Survey data (cat. no. 4500.0.55.001).

75 Country of Birth data were classified according to the Standard Australian Classification of Countries (SACC) (cat. no. 1269.0).

76 Languages spoken at home were classified according to the Australian Standard Classification of Language (ASCL) (cat. no. 1267.0).

77 Australian geographic data are classified according to the Australian Statistical Geography Standard (ASGS): Volume 1 - Main Structure and Greater Capital City Statistical Areas (cat. no. 1270.0.55.001)

78 Educational attainment data are classified according to the Australian Standard Classification of Education (ASCED) (cat. no. 1272.0)

79 The Census and Statistics Act, 1905 provides the authority for the ABS to collect statistical information, and requires that statistical output shall not be published or disseminated in a manner that is likely to enable the identification of a particular person or organisation. This requirement means that the ABS must take care and make assurances that any statistical information about individual respondents cannot be derived from published data.

80 To minimise the risk of identifying individuals in aggregate statistics, a technique has been used to randomly adjust cell values. This technique is called perturbation. Perturbation involves a small random adjustment of the statistics and is considered the most satisfactory technique for avoiding the release of identifiable statistics while maximising the range of information that can be released. These adjustments have a negligible impact on the underlying pattern of the statistics.

81 After perturbation, a given published cell value will be consistent across all tables. However, adding up cell values to derive a total will not necessarily give the same result as published totals. Where possible, a footnote has been applied to an estimated total where this is apparent in a diagram or graph (for example, if males who experienced violence and females who experienced violence don’t add to persons who have experienced violence). For commentary, please refer to the referenced data tables for confirmation of perturbation effects.

82 The introduction of perturbation in publications ensures that these statistics are consistent with statistics released via services such as TableBuilder.

83 Perturbation has been applied to 2016 PSS data published in this publication. Data from previous PSS or WSS presented in this publication have not been perturbed, but have been confidentialised if required using suppression of cells.

84 Estimates presented in this publication have been rounded. As a result, sums of the components may not add exactly to totals.

85 Proportions presented in this publication are based on unrounded figures. Calculations using rounded figures may differ from those published.

86 The ABS would like to thank the people who completed the survey. Their participation has contributed to valuable information that will help to inform public debate about violence and will help further development of policies and programs aimed at reducing the prevalence of violence in Australia.

87 The ABS acknowledges the support and input of the Department of Social Services (DSS) which, under the National Plan to Reduce Violence Against Women and their Children 2010-2022, provided funding for the 2016 PSS. A Survey Advisory Group, comprising of key government and non-government bodies, provided the ABS with advice on the information to be collected and on some aspects of survey methodology. Members of this group included representatives from State and Commonwealth Government departments, crime research agencies, service providers and academics in the field.

88 All tables, in Excel format, can be accessed from the Data Downloads. The spreadsheets present tables of estimates and percents/prevalence rates, and the corresponding Relative Standard Errors (RSEs) for estimates and Margin of Errors (MoEs) for per cents/prevalence rates. For more details regarding RSEs and MoEs, refer to the Technical Note of this publication.

89 The 2016 PSS is available as TableBuilder and Detailed Microdata products for users who wish to undertake more detailed analysis. TableBuilder is an online tool for creating tables from ABS survey data, where variables can be selected for cross-tabulation. The Detailed Microdata product is available through the ABS Data Laboratory. The Microdata Entry page on the ABS website contains links to microdata related information to assist users to understand and access microdata. Additional information on the PSS microdata products are also available via Microdata: Personal Safety Survey, Australia, 2016 (cat. no. 4906.0.55.001).

90 Customised tabulations 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.

1 The estimates in the 2016 PSS publication are based on information obtained from a sample of the Australian population. Although care has been taken to ensure that the results of the survey are as accurate as possible, there are certain factors which can affect the reliability of the results to some extent and for which no adequate adjustments can be made.

2 One such factor is known as sampling error. The key measures used to assess the impact of sampling error on the 2016 PSS estimates in this publication are described below. Such calculations were undertaken in this publication and should be kept in mind when interpreting the results of this survey.

3 Other factors are collectively referred to as non-sampling errors. For more details on sampling error as well as details on non-sampling errors, refer to the Data Quality and Technical Notes page in the Personal Safety Survey, Australia: User Guide, 2016 (cat. no. 4906.0.55.003).

4 As the 2016 PSS data was obtained from a sample of the Australian population, the impact of sampling error on estimates was closely reviewed. Sampling error (or sampling variability) is used to describe the circumstance where survey estimates differ from those that would have been produced had all persons been included in the survey. The magnitude of the sampling error associated with a sample estimate depends on the following factors:

• Sample design - the final design attempted to make key survey results as representative as possible within cost and operational constraints.
• Sample size - the larger the sample on which the estimate is based, the smaller the associated sampling error.
• Population variability - the extent to which people differ on the particular characteristic being measured. This is referred to as the population variability for that characteristic. The smaller the population variability of a particular characteristic, the more likely it is that the population will be well represented by the sample, and, therefore the smaller sampling error. Conversely, the more variable the characteristic, the greater the sampling error.
   

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