Personal Fraud methodology

1 The statistics presented in this release were compiled from data collected in the Australian Bureau of Statistics' (ABS) 2014-15 Multipurpose Household Survey (MPHS). The MPHS is conducted each financial year throughout Australia from July to June as a supplement to the ABS' monthly Labour Force Survey (LFS) and is designed to provide annual statistics for a number of small, self-contained topics.

2 In 2014-15, the topics were:

• Barriers and Incentives to Labour Force Participation
• Retirement and Retirement Intentions (including Method of Meeting Current Living Costs)
• Household Use of Information Technology
• Patient Experience
• Crime Victimisation (including Personal Fraud)
• Income (Personal, Partner's, Household).

3 For all topics, general demographic information such as age, sex, labour force characteristics, education and income are also available.

4 The Personal Fraud Survey collected information from individuals about their experience of selected personal fraud in the 12 months prior to interview (except for identity theft where persons were asked if they had ever been a victim of identity theft and then data were collected about experiences in the five years and 12 months prior to interview), and whether they incurred any financial loss. Detailed characteristics of persons who experienced fraud and incidents of fraud were also collected.

5 The scope of the LFS is restricted to people aged 15 years and over who were usual residents of private dwellings, except:

• members of the permanent defence forces
• certain diplomatic personnel of overseas governments, customarily excluded from census and estimated populations
• overseas residents in Australia
• members of non-Australian defence forces (and their dependants).

6 In addition, the 2014-15 MPHS also excluded the following from its scope:

• households in Indigenous Communities
• persons living in non-private dwellings (e.g. hotels, university residences, students at boarding schools, patients in hospitals, inmates of prisons and residents of other institutions (e.g. retirement homes, homes for persons with disabilities).

7 As indicated above, the scope of the MPHS excluded persons living in very remote parts of Australia. The exclusion of these people is unlikely to impact on state and territory estimates, except in the Northern Territory where they account for approximately 23% of the total population.

8 The coverage of the 2014-15 MPHS was the same as the scope, except that persons living in Indigenous Communities in non-very remote areas were not covered for operational reasons. 

9 In the LFS, rules are applied which aim to ensure that each person in coverage is associated with only one dwelling and hence has only one chance of selection in the survey. See Labour Force, Australia (cat. no. 6202.0) for more details.

10 The MPHS was conducted as a supplement to the monthly LFS. Each month one eighth of the dwellings in the LFS sample were rotated out of the survey. In 2014-15, all of these dwellings were selected to respond to the MPHS each month. In these dwellings, after the LFS had been fully completed for each person in scope and coverage, a person aged 15 years and over was selected at random (based on a computer algorithm) and asked the various MPHS topic questions in a personal interview. If the randomly selected person was aged 15–17 years, permission was sought from a parent or guardian before conducting the interview. If permission was not given, the parent or guardian was asked the personal fraud questions on behalf of the 15–17 year old. Data were collected using Computer Assisted Interviewing (CAI), whereby responses were recorded directly onto an electronic questionnaire in a notebook computer, usually during a telephone interview.

11 For the 2014-15 MPHS, the sample was accumulated over a 12 month period from July 2014 to June 2015.

12 The publication Labour Force, Australia (cat. no. 6202.0) contains definitions of demographic and labour force characteristics, and information about telephone interviewing that is relevant to both the monthly LFS and MPHS.

13 The initial sample for the personal fraud topic was 44,786 private dwellings, from which one person was randomly selected. Of the 37,701 private dwellings that remained in the survey after sample loss (for example, dwellings selected in the survey which had no residents in scope for the LFS, vacant or derelict dwellings and dwellings under construction), 27,341 or 73.7% fully responded to the questions on personal fraud victimisation. 

14 There have been a number of changes from the 2010-11 Personal Fraud Survey that have affected the availability or comparability of some data items in the 2014-15 Survey. Information about characteristics of incidents of personal fraud are not comparable across the two reference periods. The 2010-11 survey collected detailed characteristics about all incidents in the last 12 months for each fraud type. The 2014-15 survey collected details on the most recent incident only.

15 Some of the characteristics of the incidents that were collected also changed between 2014-15 and 2010-11. The 2014-15 survey collected data about time lost and behaviour change due to the fraud incident for each fraud type, for the first time. The 2010-11 survey collected additional data items about incidents of personal fraud types, such as information about joint account holder status, and how many cards were subjected to card fraud. 

16 Information about total financial loss for all incidents of each type of fraud in the last 12 months was collected in both 2014-15 and 2010-11 and is therefore comparable.

17 Additional questions were asked in the 2014-15 survey on the impact of fraud incidents. These included whether the respondent had discovered the most recent incident of fraud or someone else had informed them, the amount of time lost in the most recent incident, and whether their behaviour has changed as a result of the fraud incident. To accommodate these new questions, some information collected in the 2010-11 survey was not included in 2014-15: the number of cards fraudulently used, whether these were part of a joint account with another person, and the number of joint account holders.

18 Due to changes in the question regarding experience of identity theft, data from 2014-15 are not comparable with those from 2010-11. 

19 The number of response categories for 'how details were obtained' was increased in 2014-15 to reflect current common methods, such as social media. Additional questions were asked in the 2014-15 survey on the impact of identity theft incidents. These included the amount of time lost in the most recent incident, and whether behaviour has changed as a result of the fraud incident.

20 In 2014-15, additional information was collected on how the respondent became aware the incident was a scam. Additional questions were also asked on the impact of scam incidents, including the amount of time lost in the most recent incident, and whether behaviour has changed as a result of the fraud incident.

21 Some of the selected scam types included in 2014-15 differ from those in 2010-11, and it is not recommended to directly compare data by scam type. The two categories 'lottery' and 'pyramid scheme' are consistent between the two surveys. Information on additional scam types was included in 2014-15. These were: 'information request', 'relationship', 'up-front payment', 'financial advice', 'computer support', 'working from home', and 'online trading or auction site'.

22 In this survey, personal fraud comprises:

• card fraud
• identity theft
• selected scams, which include:
  • lottery
  • information request
  • pyramid scheme
  • relationship
  • up-front payment
  • financial advice
  • computer support
  • working from home
  • online trading or auction site
  • other scams.
     

23 A person was defined as having experienced identity fraud if they had their credit, debit or EFTPOS card, or other personal details or documents, such as driver’s licence, tax file number or passport, used by another person for unauthorised gain. This included instances where business transactions were conducted or accounts opened in the individual’s name without permission, or any other uses of their identity without permission. Persons who became aware of an occurrence of identity fraud against them were considered to have experienced identity fraud.

24 The survey sought to establish the number of incidents of card fraud or identity theft that were experienced, that is, the number of times the respondent had their personal or financial details stolen. The survey did not collect the number of individual transactions or cash withdrawals that occurred in each incident before the breach was detected. For example, if a respondent's card was stolen and was used to make five transactions before the card was cancelled, only the one incident of the card being stolen and used fraudulently was counted.

25 A person was defined as having experienced a scam if they were not only exposed to a scam or fraudulent offer, but also responded to a scam invitation, request, notification or offer by way of supplying personal information, money or both, or if they sought more information from the sender of the scam. 

26 A person could have experienced one or more selected personal fraud types; where this was the case they were counted in each personal fraud type. For example, a person may have experienced both a relationship scam and a lottery scam. This person would be counted in both scam categories. A total count of persons experiencing all types of personal fraud is also available, but persons are only counted once in the totals. Using the previous example, the total would only count this person once even though two incident types occurred. Components therefore will not always add to the total counts in the publication.

27 Socio-demographic characteristics, such as age, sex, labour force status and personal weekly income were collected about all respondents. The survey provides a profile of these characteristics for each type of personal fraud. 

28 Detailed characteristics (such as method of fraud, reporting of incidents, and financial loss) of each type of fraud were collected for the most recent (card fraud and identity theft) or most serious (scams) incident of each fraud type only in 2014-15.

29 For each different type of personal fraud, individuals were asked to report the amount of money they lost as a result of all incidents. For card fraud this refers to the total financial loss before any reimbursement from the card issuer. Information is reported separately for the amount of money lost after reimbursement for card fraud.

30 Where mean, median and total financial losses are reported in this publication, the total financial loss before any reimbursement from the card issuer is used. 

31 Equivalence scales are used to adjust the actual incomes of households in a way that enables the analysis of the relative well-being of people living in households of different size and composition. For example, it would be expected that a household comprising two people would normally need more income than a lone person household if all the people in the two households are to enjoy the same material standards of living. Adopting a per capita analysis would address one aspect of household size difference, but would address neither compositional difference (i.e. the number of adults compared with the number of children) nor the economies derived from living together.

32 When household income is adjusted according to an equivalence scale, the equivalised income can be viewed as an indicator of the economic resources available to a standardised household. For a lone person household, it is equal to income received. For a household comprising more than one person, equivalised income is an indicator of the household income that would be required by a lone person household in order to enjoy the same level of economic well-being as the household in question.

33 The equivalence scale used in this publication was developed for the Organisation for Economic Co-operation and Development and is referred to as the 'modified OECD' equivalence scale. It is widely accepted among Australian analysts of income distribution. 

34 The scale allocates 1.0 point for the first adult (aged 15 years and over) in a household; 0.5 for each additional adult; and 0.3 for each child. Equivalised household income is derived by dividing total household income by the sum of the equivalence points allocated to Australian household members. For example, if a household received combined gross income of $2,100 per week and comprised two adults and two children (combined household equivalence points of 2.1), the equivalised gross household income would be calculated as $1,000 per week.

35 For more information on the use of equivalence scales, see Household Income and Wealth, Australia (cat. no. 6523.0).

36 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, which, for the MPHS, can be either a person or a household. The weight is a value which indicates how many population units are represented by the sample unit. For the MPHS, the first step in calculating weights for each unit was to assign an initial weight, which is 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 (i.e. they represent 600 people).

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

38 For person estimates, the MPHS was benchmarked to the projected population in each state and territory, as at 31 March 2014. For household estimates, the MPHS was benchmarked to independently calculated estimates of the total number of households in Australia. The MPHS estimates do not (and are not intended to) match estimates for the total Australian person/household populations obtained from other sources.

39 Survey estimates of counts of persons or households are obtained by summing the weights of persons or households with the characteristic of interest.

40 To minimise the risk of identifying individuals in aggregate statistics, a technique called perturbation is used to randomly adjust cell values. 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. 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. Perturbation has only been applied to data from 2014-15.

41 For data from previous cycles (2007 and 2010-11), only cells containing small values were randomly adjusted to avoid releasing confidential information, a technique known as randomisation. One effect of randomisation is that totals may vary slightly across tables. These adjustments do not impair the value of the tables as a whole.

42 All sample surveys are subject to error which can be broadly categorised as:

•  sampling error
•  non-sampling error.
   

43 Sampling error is the difference between the published estimates, derived from a sample of persons, and the value that would have been produced if the total population (as defined for the scope of the survey) had been included in the survey. For more information refer to the Technical Note.

44 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.

45 Due to differences in the scope and sample size of the MPHS and that of the LFS, the estimation procedure may lead to some small variations between labour force estimates from this survey and those from the LFS.

46 When interpreting data from the 2014-15 MPHS, consideration should be given to the representativeness of the survey sample in relation to the entire in-scope population. This is affected by the response rate and scope and coverage rules. For example, people living in boarding houses, refuges or on the streets are excluded from this survey and may experience different levels of victimisation than those surveyed who live in private dwellings.

47 Country of birth data are classified according to the Standard Australian Classification of Countries (Second Edition) (SACC), 2011 (cat. no. 1269.0).

48 Educational attainment data are classified according to the Australian Standard Classification of Education (ASCED), 2001 (cat. no. 1272.0).

49 All data tables are available in Excel spreadsheet format and can be accessed from the Data downloads section. The data tables contain number and proportion estimates, and their corresponding relative standard errors. 

50 A further option for accessing data from the Personal Fraud Survey is to contact the National Information and Referral Service. A range of additional data not provided in the standard spreadsheets may be provided on a fee-for-service basis through ABS Information Consultancy. A spreadsheet containing a complete list of the data items available from the Personal Fraud Survey can be accessed from the Data downloads section.

51 ABS surveys draw extensively on information provided freely by individuals, businesses, governments 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.

1 The estimates in this publication are based on information obtained from a sample survey. Errors in data collection or processing, known as non-sampling error, can impact on the reliability of the resulting statistics. In addition, estimates based on sample surveys are subject to sampling error. That is, the estimates may differ from the true value of the characteristics being measured that would have been obtained had all persons in the population been included in the survey.

2 Non-sampling error may occur in any statistical 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.