3412.0 - Migration, Australia, 2011-12 and 2012-13 Quality Declaration 
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 18/12/2013   
   Page tools: Print Print Page Print all pages in this productPrint All

TECHNICAL NOTE: '12/16 MONTH RULE' METHODOLOGY FOR CALCULATING NET OVERSEAS MIGRATION FROM SEPTEMBER QUARTER 2006 ONWARDS

Background


Estimating NOM with the '12/16 month rule' methodology
Further information


BACKGROUND

1 The Australian Bureau of Statistics has developed and introduced an improved method for estimating net overseas migration (NOM). The methodology is based on the '12/16 month rule' for calculating NOM and the resulting estimates have been used in calculating Australia's official estimated resident population (ERP) since September quarter 2006. The improved method is a result of reviewing the treatment of all temporary migrants who are away from, or resident in, Australia for a period of 12 months or more.

Net overseas migration and official population estimates

2 Net overseas migration is one component of population change used to estimate the Australian resident population, as are births and deaths. Officially the estimated resident population (ERP) is based on the concept of usual residence in Australia. According to recommendations of the United Nations an international migrant is defined as 'any person who changes his or her country of usual residence'(footnote 1). For the purposes of NOM and therefore ERP, a person is regarded as a usual resident if they have been (or expected to be) residing in Australia for a period of 12 months or more. As such, the ERP includes all people, regardless of nationality, citizenship or legal status, who usually live in Australia, with the exception of foreign diplomatic personnel and their families.

3 Conceptually, the term NOM is based on an international traveller's duration of stay being in or out of Australia for 12 months or more. It is the difference between:
  • the number of incoming travellers who stay in Australia for 12 months or more, who are not currently counted within the population, and are then added to the population (NOM arrivals); and
  • the number of outgoing travellers who leave Australia for 12 months or more, who are currently counted in the population, and are then subtracted from the population (NOM departures).
With the introduction of the '12/16 month rule' methodology for estimating NOM this 12 months does not have to be continuous and is measured over a 16 month reference period. For example, whether a traveller is in, or out of, the population is determined by their exact duration of stay in Australia over the subsequent 16 months after arrival or departure.

4 In short, to be able to accurately measure people that have contributed to NOM estimates there are three main issues for consideration:-
  • Is the person in, or out of, Australia's population prior to the overseas movement?
  • Is the actual duration of stay within (or away from) Australia for at least 12 months?
  • Is the person arriving or departing Australia?
Reasons for change in methodology

5 During a reconciliation of 1996-2001 intercensal population growth estimates (including measures of immigration, emigration and NOM) with the results of the 2001 Census of Population and Housing, the ABS identified that inconsistent results were arising from a 1998 passenger card processing change and the measurement of temporary visitors' duration of stay in Australia, or Australian residents' temporary duration of absence from Australia.

6 The ABS noted that the precise measurement of duration of stay in Australia or absence from Australia using a comparison of border crossing transactions may lead to a misleading categorisation of frequent travellers to short-term (i.e. less than 12 months), when their overall period of stay or absence in a broader context was long-term (i.e. 12 months or more) punctuated by short journeys. For example, an international student in Australia for a 3 or 4 year course of study, who leaves Australia briefly each year for holiday or other reasons, would incorrectly not be added to estimates of Australia's population. This was because after the passage of time, they did not spend a continuous period of 12 months in Australia during their long-term period of stay in Australia (the previous method of measurement). This was inconsistent with the intention behind the definition of a long-term migrant as set out in the United Nations Recommendations on Statistics of International Migration, Revision 1 (1998, 18) and the ABS estimated resident population (ERP) conceptual definition. The use of single continuous periods of stay as the criteria (i.e. 12 continuous months) for classifying travellers into the non-permanent migration categories (e.g. short-term visitor, long-term visitor) was seen as a major shortcoming in the measurement of NOM and consequently estimates of Australia's resident population.

7 Further, there were some travellers such as permanent immigrants and emigrants who were not asked their intended duration of stay or absence on Australian passenger cards, yet it was observed that after a passage of less than a year, some permanent immigrants departed Australia and some permanent emigrants returned to Australia. The ABS also identified a need to convert the multiple border movements information for frequent travellers within a reference period to individual person estimates together with their travel history over time to avoid double counting.

8 The method for estimating NOM was reviewed in 2004 in response to the issues arising with the previous estimation of category jumping, i.e. changes between stated intention and actual duration of stay of travellers to/from Australia. The review also addressed the changing patterns of travel into, and out of, Australia, in particular the increased propensity for travellers to interrupt longer periods of stay or absence with short-term trips.

9 The methodology and estimation system adopted by the ABS (i.e. the 12/16 month rule) for measuring NOM and the contribution to Australia's ERP, more closely aligns with the international definitions set out by the United Nations. The ABS has not changed the statistical conceptual definition of net overseas migration. However, the method of measurement has changed.

Change in methodology to improve NOM estimation

10 In 2007, to better measure the changes in traveller behaviour and in particular to more accurately capture and measure temporary migration, the ABS introduced the '12/16 month rule' methodology for calculating NOM. The key improvements were:
  • the introduction of the '12/16 month rule', whereby a traveller is included in the resident population if they are in Australia for a total of 12 months or more over a 16 month period, or conversely, subtracted from the population if they are away for a total of 12 months or more over a 16 month period; and
  • the shift from a movements-based approach to a traveller-based approach for estimating NOM. This is done through assembling administrative data using a unique personal identifier to create individual traveller histories.

11 This has replaced the previous method (12/12 month rule) where a traveller had to be in, or away from, Australia for 12 continuous months. With this methodology many overseas travellers with short-term interruptions to a longer period of stay/absence (e.g. international students studying in Australia) may have been continually excluded from NOM estimates. In addition, this previous method did not measure the exact duration of stay for all travellers but used their intended duration of stay.

12 The current methodology (12/16 month rule) has been calculated from December quarter 2003 to test systems and for quality assurance purposes. This was undertaken before the official release of these new NOM data from the 1 July 2006 when it was used in producing Australia's official estimated resident population (ERP) figures. Prior to this date, the previous methodology (12/12 month rule) had been used to produce the official ERP figures. The change in method has therefore resulted in a break in the official NOM time series at 30 June 2006.

13 Analysis undertaken by the ABS comparing the previous method (12/12 month rule) to the current method (12/16 month rule) over a three year period (December quarter 2003 to September quarter 2006), shows the current method estimate to be on average 25% higher than the previous estimate.

Source of overseas migration data

14 The ABS statistics on overseas migration are calculated using administrative data collected and compiled by the Department of Immigration and Citizenship (DIAC) under the authority of the Migration Regulations (Migration Act, 1958). At present, the main source of data on overseas migration is the incoming and outgoing passenger cards completed by all persons arriving in or departing from Australia. Data from passports and visa (entry permit) applications and approvals are also provided by DIAC's Travel and Immigration Processing System (TRIPS). Information from these three data sources is collected, compiled and matched together by DIAC.

15 Quarterly NOM estimates are sourced from the processed monthly overseas arrivals and departures (OAD) data (compiled using matched TRIPS data) and monthly extracts of unmatched TRIPS records. Unmatched TRIPS records are those where a movement has been recorded by DIAC within the TRIPS system but the data have not been able to be matched with either a passenger card, passport or visa permit.

16 Statistics from the NOM collection exclude: multiple movements; the movements of operational air and ships' crew; transit passengers who pass through Australia but are not cleared for entry; passengers on pleasure cruises commencing and finishing in Australia and undocumented arrivals. From 1 July 2006 onwards, foreign diplomatic personnel and their families are also excluded.

17 Quarterly NOM estimates contribute to quarterly ERP and are released in Australian Demographic Statistics (cat. no. 3101.0). The annual Migration, Australia publication (cat. no. 3412.0) provides annual data and analysis on NOM. It also includes a time series based on the improved methodology from 2004 onwards, is updated every six months and is released electronically as a data cube (in Supertable format) from the Downloads tab. Statistics on OAD and related data quality issues are published on a monthly basis in Overseas Arrivals and Departures, Australia (cat. no. 3401.0).

Clarification of data sources used to analyse overseas migration

18 There are a number of data sources that can be used in the analysis of overseas migration. However, there are three main data sources that can be often confused on the measurement of the event of overseas migration. They include:
  • the number of travellers from the NOM collection;
  • the number of movements from the OAD collection; and
  • the number of visas being granted.

19 It is data on the number of travellers from the NOM collection on which accurate migration estimates are based. It is these NOM estimates that are used in the official estimates of Australia's resident population, not the number of OAD movements or the number of visas granted.

20 Statistics from the OAD collection relate to the number of movements of travellers rather than the number of travellers (i.e. multiple movements of individual persons during a given reference period are each counted separately). The OAD collection also relates to information self reported by most travellers on their intended duration of stay in, or away from, Australia. Therefore, movement data from the OAD collection would always be different to the official estimation of the number of travellers from the NOM collection.

21 The Australian Department of Immigration and Citizenship (DIAC) manages and grants visas each year in accordance with relevant legislation, government planning and policy. It is important to note that there is a difference between when and how many visas are granted by DIAC; and when and how they may impact on NOM and therefore Australia's estimated resident population (ERP). For example, for many visas there can be a lag between a visa being granted and the actual use of that visa by the applicant on entering Australia. Also, some travellers who have been granted permanent or long-term temporary visas may end up staying in Australia for a short period of stay or not at all and therefore will not have contributed to NOM as they do not meet the '12/16 month rule' (see Glossary). In addition, travellers may also apply for, and be granted, a different visa whilst in Australia or overseas. Therefore, the number of visas granted would always be different to the official estimation of the number of travellers from the NOM collection.

22 Care should be taken when using either OAD movements data or the number of visas granted, as these sources are not the best suited for measuring overseas migration in the context of contributing to official population estimates for Australia.

Diplomatic personnel

23 Australia's ERP and estimates of NOM include all people, regardless of nationality, citizenship or legal status, who usually live in Australia, with the exception of foreign diplomatic personnel and their families. Therefore, foreign diplomatic personnel and their families are considered out of scope and were removed from NOM estimates from 1 July 2006. The previous methodology for estimating NOM was unable to exclude diplomatic personnel and their families. However, with the improved NOM methodology, refinements to the NOM processing system have enabled this to occur through the use of visa information.

ESTIMATING NOM WITH THE '12/16 MONTH RULE' METHODOLOGY

24 The current NOM estimation methods employ a '12/16 month rule' where the traveller can be added to, or subtracted from, NOM if they have stayed in, or been absent from, Australia for a period of 12 months or more over a 16 month period. This period of 12 months does not have to be continuous. Although a traveller states their intended duration of stay on a passenger card, for NOM purposes the ABS now measures an individual's actual travel behaviour.

25 To measure a traveller's actual duration of stay the ABS uses a unique personal identifier provided with the administrative data supplied by DIAC. To be able to apply the '12/16 month rule', the personal identifier is used to match a traveller's movements over time and construct a movement history for each arrival and departure record.

Conversion of overseas movements to travellers

26 Conceptually, NOM estimates should be based on counts of travellers, rather than counts of overseas movements, since travellers may have more than one movement in a particular reference period. Under the previous system of NOM estimation, a number of adjustments to overseas arrivals and departures were required. These mainly comprised adjustments for a traveller's duration of stay, designed to reflect differences between their stated travel intention and actual travel behaviour. However, adjustments were also required to transform numbers of overseas movements into numbers of travellers.

27 One of the central changes with the '12/16 month rule' methodology is that all estimation is based on actual individual travellers and their travel histories (using de-identified data), rather than in the previous methodology when an aggregation of movements represented travellers.

28 At the time a traveller crosses Australia's border it is not empirically known how long they will spend in Australia (for an arrival) or overseas (for a departure). A key change for estimating NOM is a shift to a traveller-based approach that matches an individuals' border movements over time and creates individual traveller histories. The ABS now records their actual duration of stay over the 16 month reference period and accounts for any multiple movements that may have occurred. Previously the ABS based NOM estimates on a synthesis of movements which were converted to represent a traveller.

29 The difference between the number of movements and the number of travellers who make these movements, based on the '12/16 month rule' methodology, is seen in the diagram below.

CONVERSION OF OVERSEAS MOVEMENTS TO TRAVELLERS - 2006 - 07
Diagram: CONVERSION OF OVERSEAS MOVEMENTS TO TRAVELLERS


30 For 2006-07, the number of movements was 23,757,300 (the sum of all arrivals and all departures). Using the '12/16 month rule' methodology for calculating NOM, the number of movements is converted to travellers to become 13,294,000 travellers. Therefore in the financial year 2006–07, there were over 10 million multiple movements accounting for 44% of all movements for the year.
Conversion of travellers contributing to net overseas migration

31 All travellers (excluding foreign diplomatic personnel, their families and transport crew) are included in calculating NOM which is based on a traveller's actual measured duration of stay. Under the '12/16 month rule' methodology for calculating NOM, all traveller arrivals and all traveller departures are potential contributors to NOM, as seen in the diagram below.

32 Before a traveller can contribute to the NOM estimate, a series of migration adjustments and derivations are applied to reflect each individual traveller's actual travel behaviour (or expected for preliminary estimates). Through a number of these adjustments and derivations, calculations are undertaken for each and every traveller (both arrivals and departures), to ascertain who contributes to the NOM estimate for a given reference quarter. The method is applied each quarter. The annual NOM estimate is the sum of the four quarterly NOM estimates for corresponding period. For detailed information of migration adjustments and derivations used see Chapter 6, Estimating Net Overseas Migration in Population Estimates: Concepts, Sources and Methods, 2009 (cat. no. 3228.0.55.001).

CONVERSION OF TRAVELLERS CONTRIBUTING TO NOM - 2006 - 07
Diagram: CONVERSION OF TRAVELLERS CONTRIBUTING TO NOM


33 The number of travellers are converted into NOM arrivals and NOM departures. In other words, those who stayed in (or away from) Australia for a period of 12 months or more over a 16 month reference period. NOM arrivals are the number of incoming international travellers who stay in Australia for 12 months or more, who are not currently counted within the population, and are then added to the population. NOM departures are the number of outgoing international travellers (Australian residents and long-term visitors to Australia) who leave Australia for 12 months or more, who are currently counted within the population, and are then subtracted from the population. NOM estimates are therefore the net gain or loss of population through immigration to Australia (NOM arrivals) and emigration from Australia (NOM departures).

34 For 2006-07, these conversions resulted in a final NOM estimate of 232,800 people who were added to the nation's population. This was 1.0% of all movements across Australia's borders for the year and 1.8% of all travellers who crossed Australia's borders during the same period.
FINAL NOM ESTIMATION

35 It is with the final NOM estimates that the '12/16 month rule' can be fully applied. A traveller's actual duration of stay can only be calculated when data on overseas movements become available for the full 16 months following a reference period. Currently, the final NOM estimates based on the '12/16 month rule' are considered to be of high quality.

36 Processing the final estimation of NOM provides, for each traveller in the reference quarter, a 'migration adjustment' based on their 'initial category of travel' (see Glossary).

37 The 'initial category of travel' has a key role in making preliminary estimates of NOM. It is determined by a number of dimensions:
  • direction of travel - either an arrival or departure;
  • residence status - either a visitor or Australian resident (identified by the traveller themselves on the passenger card); and
  • duration of stay in Australia (or overseas) which can be either:
      • permanent traveller;
      • long-term traveller - has an initial duration of stay (or absence) of one year or more; or
      • short-term traveller - has an initial duration of stay (or absence) of less than one year.
For a visitor arriving and resident departing, it is their intended duration of stay that is recorded, whereas for a visitor departing and resident returning it is their measured duration of stay since the previous Australian border crossing that is recorded.

38 The 'initial category of travel' is also determined at the time of the movement. However, all travellers are assigned to one, and only one, category of travel during a reference quarter. Further information and a list of the ten 'initial categories of travel' are detailed in the Glossary.

39 The migration adjustment, created during final NOM processing, is the difference between the traveller's true behaviour (actual duration of stay and its effect on ERP status) as recorded in final NOM and what was deduced from their 'initial category of travel'. In other words, an adjustment is made to correct if they should have initially been counted in, or out of, the population for the reference quarter. The 'migration adjustment' is not required to determine final NOM estimates, but is essential for estimating future preliminary NOM.
Implausible travel sequences

40 There are circumstances where implausible travel sequences appear in the data. For example, a traveller is recorded as having two sequential arrivals in Australia without a departure in between, or conversely, two departures from Australia without an arrival. In these instances the implausible travel sequences are repaired using a logical imputation. The repair of implausible sequences is necessary in order to derive an estimate of duration of stay or absence, since time spent in Australia is derived by summing up the duration between each arrival and departure pair.
Final NOM estimation - steps undertaken

41 Final NOM estimates are calculated in the following sequential order.

Step 1: Derive person-level data on overseas movements

42 Data from the Overseas Arrivals and Departures (OAD) collection, along with additional data obtained from the Travel and Immigration Processing System (TRIPS) which are sourced from DIAC.

43 Each OAD file contains information derived from incoming and outgoing passenger cards, and is matched for each movement to selected TRIPS data items through a unique personal identifier. OAD files do not include records where a passenger card has not been matched to TRIPS (e.g. if the traveller records incorrect passport details on their passenger card, and the mismatch between this and the TRIPS record has not yet been resolved). Records from TRIPS relating to these unmatched movements are extracted and added to the quarterly OAD files for NOM estimates.

44 The quarterly files used for NOM estimates also contain a number of logical edits and imputations, mainly at the movement level. Person-level data are constructed from these movement data by matching movements using personal identifiers.

Step 2: Determine the category of travel for each overseas traveller

45 Travellers are assigned to one, and only one, category of travel during a reference quarter. The algorithm used to assign a category of travel to each traveller is based on:
  • the last movement during the reference quarter where the traveller stated an intention to remain in Australia or overseas for 12 months or more (i.e. permanent arrival, permanent departure, long-term visitor arrival or long-term resident departure movements); otherwise,
  • their first movement during the reference quarter (i.e. long-term resident return, short-term resident return, short-term visitor arrival, long-term visitor departure, short-term resident departure and short-term visitor departure) during the reference quarter.

Step 3: Derive ERP flag at start of reference quarter

46 An 'ERP flag' is used to indicate whether a traveller is 'IN' or 'OUT' of the ERP at the start of the reference quarter. During the start-up period for the improved NOM methods, this flag has been determined by looking at the individual's previous travel history.

47 For subsequent periods, a traveller's ERP flag at the start of a reference quarter will be carried forward from their flag at the end of the previous quarter. If the traveller has no flag in any of the previous six quarters, their ERP flag at the start of the reference quarter will be imputed based on the direction of their first movement within the quarter i.e. 'OUT' of ERP if they are arriving in Australia; 'IN' ERP if they are departing from Australia.

Step 4: Derive movement history and required data items for each overseas traveller

48 Movement histories are constructed for each traveller based on their overseas arrivals and departures during the 16 months following an overseas movement that takes place in the reference quarter. In addition, a number of key demographic data items are derived for each traveller, including their financial year of birth (used to calculate age at 30 June), sex, country of birth and country of citizenship. In most cases these derived items are available from the source OAD and/or TRIPS datasets. In cases where required demographic data items are missing, logical imputations similar to those applied in existing OAD and ERP systems are used.

Step 5: Identify implausible movement sequences, and impute 'missing' movements

49 Implausible movement sequences appear in the data for a number of reasons, but are mainly due to non-matches between travel information (i.e. visa applications or passport information) and existing TRIPS information. Non-matches can occur when a traveller's personal details change (e.g. marital status, family name), or when their travel documentation is updated (e.g. new passport and country of passport, perhaps combined with changes to personal details). When a non-match occurs, the DIAC processing systems assign a new personal identification number to the movement before referring it to a resolution process. While most non-matches are resolved at a later date, administrative data provided to the ABS for the OAD or from TRIPS may not include all revisions relating to this process.

50 Some travellers with implausible movement sequences in the data will also have a sequence (before and/or after the implausible sequence) of plausible movements over the 16 month period studied. In these cases, an assumption is made that the proportion of a traveller's time spent in Australia during the implausible movement sequence was consistent with their proportion of time spent in Australia during plausible movement sequences. Using their plausible movement sequences, a ratio of their time spent in Australia to their time spent overseas is calculated and applied to the implausible sequence to impute a 'proxy' arrival or departure movement.

51 For a very small number of travellers, there may be no plausible movement sequence in the data during the 16 month period analysed (e.g. a movement history may only show two or more overseas arrivals, or only show two or more overseas departures). It is assumed that these travellers spent 50% of the time between movements in Australia.

Step 6: Determine the total duration of stay for each traveller and calculate ERP flags

52 As part of the '12/16 month rule' methodology used for final NOM estimation, the total duration of stay/absence for each traveller is determined by adding each of their durations of stay/absence as shown by movement histories over the 16 month period following their initial overseas movement.

53 As shown in the following diagram, the actual duration of stay is used to calculate whether a traveller who is 'IN' or 'OUT' of the population (ERP) before the movement is 'IN' or 'OUT' of the population (ERP) after the movement, regardless of their intended duration of stay.

DERIVATION OF ESTIMATED RESIDENT POPULATION (ERP) FLAGS
Diagram: DERIVATION OF ESTIMATED RESIDENT POPULATION (ERP) FLAGS


Step 7: Calculate NOM estimates and final impact on the ERP

54 Each traveller moving into the population (ERP) during a reference quarter is added to the total NOM estimate for the quarter. Similarly, each traveller moving out of the population (ERP) is subtracted from the NOM estimate. Travellers whose initial and final ERP status for the quarter are the same make no contribution to NOM.

Step 8: Migration adjustment value

55 For final estimation, a 'migration adjustment' (MA) value is derived for each traveller in the reference quarter, as a by-product. The MA value is equal to the difference between the traveller's actual contribution to NOM for the quarter (i.e. -1, 0 or +1) and their initial contribution to NOM based solely on their category of travel (i.e. +1 for a permanent or long-term arrival, -1 for a permanent or long-term departure, and 0 for a short-term arrival or departure). The MA value is not required to determine final NOM estimates for the reference quarter, but is used for estimating preliminary NOM for the corresponding quarter two years later.
State or territory of usual residence

56 The distribution of improved NOM estimates across states and territories is based on information as reported by travellers on incoming and outgoing passenger cards. There are two data items (State 1 and State 2) that are derived to determine a traveller's state or territory of residence/stay.

State 1

57 Derivation of the first data item (State 1) is dependent upon the direction of travel (either arrival or departure) and on the type of traveller (either visitor or a resident). For a visitor arrival the state or territory of residence (State 1) is the state or territory where they intend to stay (as indicated on the incoming passenger card). For a visitor departure it is the state or territory in which the traveller states they spent the most time. For a resident arrival it is the state or territory of their intended address in Australia, and for a resident departure it is the state or territory in which they lived. This information is obtained from incoming and outgoing passenger cards.

State 2

58 As a short-term visitor to Australia may move state or territory during their time in Australia, the second data item (State 2) is used to code them to the state or territory where they spent the most time as reported on their subsequent outgoing passenger card.

59 For example, if a short-term visitor arrives in June 2005 and this is their first arrival in Australia, they are allocated to the state or territory they have indicated on their passenger card as their state of intended stay (State 1). However, it is only possible to finalise their contribution to ERP for a reference quarter through the collection of future data i.e. the 16 months following the reference quarter. Therefore, a traveller history is collected over 16 months after the June 2005 reference quarter. If it is found through the traveller's history that they have stayed 12 out of 16 months, then in the June 2005 reference quarter this traveller would be allocated a State 2 value based on their outward movement subsequent to their category of travel movement (i.e. as stated on their passenger card). This would occur regardless of whether they had made numerous arrivals and departures during the 16 month period.

60 If it is found over time that the traveller has not stayed in Australia 12 out of 16 months they keep their State 1 allocation for the reference quarter, and as they have not met the required length of time for residency they will not be counted in final NOM.

61 State 2 is also derived for short-term visitor arrivals who did not leave Australia at all during the 16 months follow-up period. State or territory of residence for this group is imputed using the State 1 and State 2 distributions of long-term and short-term visitors who have spent more than 12 months, out of 16, in Australia and have made a subsequent departure movement.
PRELIMINARY NOM ESTIMATION

62 Preliminary estimates of NOM are required within six months after the end of the reference quarter for the production of quarterly ERP of Australia and each of the states and territories. At that time, complete traveller histories for the 16 months following a reference quarter are not available.

63 To estimate preliminary NOM, the ABS developed a propensity model that uses the migration adjustments derived from final NOM estimates one year earlier. Migration adjustments are calculated from changes in traveller behaviour recorded from final NOM estimates for the same type of travellers one year earlier. These migration adjustments are applied to travellers who are grouped according to their 'initial category of travel', age, country of citizenship and state or territory of usual/intended residence. The adjustment accounts for differences between a traveller's intended duration of stay and their actual duration of stay.

64 In forming the cross-classified groups of travellers for which the average migration adjustment values are derived at final estimation (for later use in preliminary estimates), the following categories are used:
  • 'initial category of travel' has a list of ten categories of travel — detailed in the Glossary.
  • state is divided into eight categories (New South Wales, Victoria, Queensland, South Australia, Western Australia, Tasmania, the Northern Territory and the Australian Capital Territory). Other Territories are not included
  • country of citizenship is divided into five groups:
      • Australia including external territories
      • New Zealand
      • South-east and North-east Asia
      • North-west Europe and North America
      • Other
  • age is divided into eight groups (0-4, 5-14, 15-19, 20-24, 25-34, 35-44, 45-54, 55+).

65 With a longer time series of final NOM estimates now available, the ABS is undertaking an examination to improve the cross-classified groupings of travellers that are used by the propensity model.
Improvements to preliminary NOM estimation

66 In 2009, timetable changes introduced with the Federal Financial Relations Act 2009, enabled the use of an additional quarter of travellers' movement data allowing for the methodology used in preliminary NOM estimates to be improved. Using the additional one quarter of movement data (the quarter after the reference period) has enabled two key changes to the methodology for estimating preliminary NOM:
  • changing from a 'two year ago' to a 'one year' ago propensity model; and
  • reducing the pool of travellers using the propensity model.

67 A 'two year ago' propensity model using the '12/16 month rule' methodology for estimating preliminary NOM was used in official ABS population estimates from September quarter 2006 until June quarter 2008.

68 The 'one year ago' (with reduced pool of travellers) propensity model using the '12/16 month rule' methodology for estimating preliminary NOM has been used in official ABS population estimates since September quarter 2008. The first release of the 'one year ago' propensity model for estimating preliminary NOM was in the September quarter 2009 issue of Australian Demographic Statistics (cat. no. 3101.0).
Changing from a 'two year ago' to a 'one year ago' propensity model

69 Under the 12/16 rule, it can take up to 16 months after the reference quarter to determine an individual traveller's ERP status of being counted in or out of Australia's population. Since full movement histories are not available within the required time frame, preliminary NOM estimates are modelled using the migration adjustments from final NOM for an earlier period. Previously, adjustments were made based on the corresponding quarter two years earlier. The final NOM from two years earlier was used as the method needed to allow a full 16 months of data to accumulate before the final NOM could enable production of exact migration adjustments for a corresponding quarter. With the previous release schedule for ERP (prior to 2010), only 12 months of movement data were available. This was insufficient to produce exact migration adjustments for the corresponding quarter one year earlier. To be able to produce an 'exact one year ago' model would require a full 16 months of data to accumulate to be able to calculate final NOM estimates and the migration adjustments necessary for use in the propensity model. Currently it would require an additional four months of movement data post reference period.

70 However, by using an additional three months (one quarter) of movement data post reference period, 15 months of movement records become available for the propensity model. Analysis showed that 15 months of movement data provide enough information to produce migration adjustments for the corresponding quarter one year earlier. The analysis revealed that using the full 16 months of movement records in an 'exact one year ago' propensity model only very marginally improved results (i.e. less than 1%) when compared to using 15 months of movement data in an 'approximate one year ago' model.

71 The 'approximate one year ago' propensity model uses a combination of 'one year ago' and 'two year ago' propensities. First, the 15 months of movement data available are used to resolve the ERP status of as many travellers as possible (almost all travellers) for the corresponding quarter one year earlier. Second, the model uses this group of travellers to calculate 'one year ago' propensities that are then used for the majority of travellers with similar characteristics in the current reference quarter. Each quarter there is a small number of travellers whose ERP status remains indeterminate after processing the 'one year ago' propensities. For this small group, a 'two year ago' propensity is calculated and then applied to travellers with similar characteristics in the current reference quarter.

72 For example, if processing September quarter 2009 (July, August and September 2009), using one additional quarter of movement data (October, November and December 2009) means the ERP status can be resolved for almost all travellers in the corresponding quarter one year earlier (September quarter 2008) using the 12/16 rule. Therefore, final NOM and migration adjustments necessary for the propensity model can be calculated for almost all of these travellers, including all travellers in the first two months in the quarter (e.g. July and August 2008). July 2008 has 16 months of movement records available at November 2009, August 2008 has 16 months of movement records available at December 2009, whereas September 2008 only has 15 months of movement records available at December 2009. However, the ERP status of many travellers in the last month (e.g. September 2008) can also be resolved with only 15 months of movement records available (e.g. as at December 2009). For example, any overseas traveller who has already recorded a duration of stay in Australia for more than 12 months is considered in Australia's population as it would no longer be possible for them to be counted out of the population. Conversely, any overseas traveller who has recorded a duration of stay away from Australia for more than four months is considered out of Australia' population as it would no longer be possible for them to be counted in the population. For those travellers whose ERP status is still unresolved, a 'two year ago' propensity (e.g. from September 2007) is calculated and then used.

73 With the need to provide timely preliminary NOM estimates, the ABS will now use the 'approximate one year ago' model as there is very little improvement made (i.e. less than 1%) by waiting one additional month to complete the full 16 months to produce exact migration adjustments for the corresponding quarter one year earlier.
Reducing the pool of travellers using the propensity model

74 Many travellers' ERP status can be determined in a much shorter time frame than the full 16 months. With the availability of this additional one quarter of movement data and applying the conditions of the 12 out of 16 month rule, many of the travellers' ERP statuses can be resolved. For example, if processing the September quarter (July, August and September) using one additional quarter of movement data (October, November and December), then for the months of July and August a minimum of four months' extra movement data have become available. July has four extra months of movement data by the end of November; and August has four extra months of data available by the end of December. In essence, any overseas traveller who has reached a recorded duration of stay out of Australia of four months or more is then considered out of Australia's population as it would no longer be possible for them to be in Australia for more than 12 out of 16 months. This reduces by around half, the number of travellers for which the propensity model needs to be applied to when estimating preliminary NOM.
FURTHER INFORMATION

75 For further information on the improvements to preliminary NOM estimation and changes to the revision schedule for NOM, see the Information Paper: Improving Net Overseas Migration Estimation, Mar 2010 (cat. no. 3412.0.55.001). For further information on the '12/16 month rule' methodology see the Information Paper: Statistical Implications of Improved Methods for Estimating Net Overseas Migration, Australia, 2007 (cat. no. 3107.0.55.005), and the Information Paper: Improved Methods for Estimating Net Overseas Migration, Australia, 2006 (cat. no. 3107.0.55.003). For information on the previous estimation methods used, September quarter 2001 to June quarter 2006, see the Technical Note in the Explanatory Notes tab of Migration, Australia, 2006-07 (cat. no, 3412.0).


1 United Nations 1998, Recommendations on Statistics of International Migration, Revision 1, Statistical Series M, No 58, Rev. 1, New York: Department of Economic and Social Affairs, Statistics Division. <back