|Page tools: Print Page Print All RSS Search this Product|
3 These statistics are important as input to a broad range of other statistical collections, including:
4 A number of characteristics collected about travellers are also available in this release. For more information and a complete list of variables available see Explanatory Note 38.
SOURCE OF THE STATISTICS
5 Administrative information on persons arriving in, or departing from, Australia is collected via various processing systems, passport documents, visa information, and incoming passenger cards (see Passenger Card Appendix). Aside from persons travelling as Australian or New Zealand citizens, persons travelling to Australia are required to provide information in visa applications. These administrative data are collected by the Australian Government Department of Home Affairs (Home Affairs) under the authority of the Migration Regulations 1994 made under the Migration Act 1958.
6 ABS statistics on overseas arrivals and departures (OAD) are mainly compiled using information from Home Affairs sources. All overseas movement records are stored on Home Affairs' Travel and Immigration Processing System (TRIPS). Each month all OAD movement records, including those matched to an incoming passenger card, are supplied to the ABS and then processed. From July 2017, due to the removal of the outgoing passenger card, the ABS has also used Medicare enrolment data as a secondary source of State of residence information for Australian residents.
7 Overseas arrivals and departures statistics relate to all recorded movements of travellers who cross Australia's international border. The statistics record the number of movements of travellers rather than the number of travellers (i.e. multiple movements of an individual traveller during a given reference period are each counted separately). It includes the movements of all travellers regardless of their nationality, citizenship or legal status.
8 The statistics exclude the movements of operational air and ships' crew, of transit passengers who pass through Australia but are not cleared for entry (including some defence force personnel), and of passengers on pleasure cruises commencing and finishing in Australia. These statistics also exclude undocumented arrivals or departures.
9 From 1 July 2016, Norfolk island was integrated into Australia for administrative purposes. Travel between Australia and Norfolk Island is no longer considered an international movement and is therefore not included in Overseas Arrivals and Departures statistics.
ESTIMATION SAMPLING METHOD
10 OAD statistics are usually derived from a combination of full enumeration and sampling. However, from April 2020 a full sample has been undertaken due to the small volume of international travel movements caused by the impact of COVID-19. All permanent arrivals and all arrivals with a duration of one year or more (long-term arrivals) have always been fully enumerated. From July 2007, all departures have been fully enumerated.
11 Prior to April 2020 all arrivals with a duration of less than one year (short-term arrivals) were sampled. While the total number of travellers and their citizenship was fully known, statistics for other characteristics of short-term arrivals (such as their state/territory of stay/residence) were based on a sample and may differ slightly from those that would be obtained from complete processing. The sample was a fixed skip based on a threshold selected by country of citizenship. The sample was designed so that countries of citizenship associated with a small number of movements were fully sampled, while countries with a larger number of movements tended to have a higher threshold. This approach minimised the effect of sampling error associated with the available statistics. When the threshold was reached, the passenger card was selected and data extracted. For example, every 55th short-term Australian arrival card was selected and the data extracted and fully quality assured for that specific card, while every single passenger card for a traveller with Sierra Leone citizenship would be selected. From July 2007 to April 2020, about 5% of all short-term arrivals were selected for sample.
12 Some statistics relating to these movements are therefore estimates which are subject to sampling variability, that is, they may differ from statistics which would have been obtained if details of all these movements had been processed. The sampling error associated with any estimate can be estimated from the sample results and one measure so derived is the standard error. It would be impractical however, to publish estimates of standard errors for all figures from OAD statistics in individual tables.
CORRECTIONS AND IMPUTATIONS
13 The imprecision due to sampling errors should not be confused with errors arising from imperfections in reporting, which may occur in any data collection, whether sampled or not. Errors of this kind differ from discrepancies arising from the fact that certain information reflects the travellers' intentions at the time the passenger cards were completed. These intentions are, of course, subject to change. Particularly affected is the distinction between permanent and temporary movement and in the latter case, duration of intended stay, country in which most time will be spent and main reason for journey.
14 Every effort is made to minimise such errors, both through careful design of the passenger cards and through checks on the information once it is received. During the edit process some items are corrected where they conflict with other known information. There are also a number of derivations and imputations undertaken that improve the quality of variables with missing responses. First, the ABS utilises alternate sources where available. The sources currently available from Home Affairs include: all overseas movements data stored on the TRIPS system, monthly missing country of birth data, and monthly New Zealand passport data. An additional alternate source used for state or territory of residence is Medicare enrolment data. Second, a hot deck imputation method is used for any remaining missing responses. For more information see Section 4 available in the Data Quality Issues (Data Quality Issues Appendix) in the Explanatory Notes section of this release.
THE 2017 REVIEW OF OAD STATISTICS AND BREAK IN SERIES
15 From 1 July 2017, travellers leaving Australia were no longer required to complete an Outgoing Passenger Card (OPC). Due to the removal of the OPC by the Department of Home Affairs, the ABS undertook a review of its Overseas Arrivals and Departures (OAD) statistics, methodology and processing systems. This provided an opportunity to consider alternative data sources and ways to make better use of a range of existing data collected by Home Affairs about Australia's international border crossings. Detailed information on the changes and improvements arising from the 2017 review of OAD statistics appears in the Data Quality Issues (Data Quality Issues Appendix) in the Explanatory Notes section of this release.
16 The review has resulted in a break in series, necessitating a revised time series for OAD data from July 2007 to June 2017 based on the new methodology. Figures prior to June 2007 may not be strictly comparable to those which follow.
17 The classification of countries in this release is the Standard Australian Classification of Countries, 2016. For more detailed information, refer to the ABS release Standard Australian Classification of Countries, 2016 (cat. no. 1269.0). The entire historical series has been backcast using this version of the classification.
18 The statistics on country of residence or main destination, and country of embarkation or disembarkation have certain limitations because of reporting on passenger cards. For example many travellers just list the UK on their passenger card rather than stating England, Scotland, Wales, or Northern Ireland.
STATE AND TERRITORY CLASSIFICATION
19 Following the 1992 amendment to the Acts Interpretation Act to include the Indian Ocean Territories of Christmas Island and the Cocos (Keeling) Islands as part of geographic Australia, population estimates commencing with September quarter 1993 include estimates for these two territories. To reflect this change, another category of the state and territory classification has been created, known as Other Territories. From 1 July 2016 Norfolk Island has been included in the Other Territories category following the introduction of the Norfolk Island Legislation Amendment Act 2015. Other Territories includes Norfolk Island, Jervis Bay Territory, Christmas Island and the Cocos (Keeling) Islands. OAD data for Other Territories are not available prior to February 1995.
SEASONAL ADJUSTMENT AND TREND ESTIMATES
20 Seasonally adjusted and trend estimates of short-term overseas movements are shown in tables 1, 3, 4, 7 and 8. Trend estimates have been suspended from February 2020 and seasonally adjusted estimates have been suspended from April 2020 due to the impact of the COVID-19 pandemic on international travel. Please see the end of the Data Quality Issues Appendix.
21 Seasonally adjusted estimates are derived by estimating and removing systematic calendar-related effects from the original series. In the short-term visitor arrival and short-term resident return series, these calendar-related effects include seasonal (e.g. increased travel in December due to the Christmas holiday period), moving holiday (e.g. increased travel in January in some years and February in others due to Lunar New Year celebrations) and trading day influences (arising from the varying length of each month, the composition of the days of the week in a month, and the varying levels of activity for different days of the week). Each influence is estimated by separate factors which, when combined, are referred to as the combined adjustment factors.
22 For March 2020, seasonal factors for both the short-term visitor arrival and short-term resident return series were calculated using data up to and including February 2020, then forecast for March 2020. This approach, known as the forward factor method, ensures that the seasonal factors are not distorted by COVID-19 impacts. The forward factor method of seasonal adjustment uses data up to a fixed point in time to estimate seasonal factors. These factors are then forecast to provide seasonal factors for the next 12 months. This process is repeated annually to calculate seasonal factors for the coming year. Seasonal factors for previous years are also revised at this point.
23 From August 2019, the ABS improved the method for calculating trend estimates. It changed by removing the "ripple" effects, which tend to be more inherent in the previous trend series for smaller series and lower level estimates. The result of removing these "ripple" effects is trend estimates which are less volatile and less prone to revisions over time. An article prepared for the March 2018 issue of Labour Force, Australia (cat. no. 6202.0) explaining the new method can be accessed here: Improvements to Trend Estimation
24 From July 2007, the ABS improved the method of producing seasonally adjusted estimates, focussing on the application of Auto-regressive Integrated Moving Average (ARIMA) modelling techniques, which can improve the revision properties of the seasonally adjusted and trend estimates. For more information on the details of ARIMA modelling, see 'Feature article: Use of ARIMA modelling to reduce revisions' in the October 2004 issue of Australian Economic Indicators (cat. no. 1350.0).
25 From November 2004, the ABS improved the method for removing trading day effects from seasonally adjusted estimates. Corrections for trading day effects are now applied as prior corrections to the original estimates, rather than being applied within the seasonal adjustment process. This is now consistent with the treatment of any corrections for large extremes, changes in level, changes in seasonal pattern, Easter, and other effects.
26 From July 2003, concurrent seasonal adjustment methodology was used to derive the combined adjustment factors. This means that data from the current month are used in estimating the combined adjustment factors for the current and previous months. Concurrent seasonal adjustment replaces the forward factor methodology used since seasonal adjustment of short-term visitor arrivals began in 1969 and short-term resident departures in 1976.
27 Concurrent adjustment can result in revisions each month to the seasonally adjusted estimates for earlier periods. However, in most instances, the only noticeable revisions will be to the combined adjustment factors for the current month, the previous month and the same month a year ago. Although there is no specific information paper on concurrent adjustment to short-term visitor arrivals or resident departures, more detail on the method in general can be found in the Information Paper: Introduction of Concurrent Seasonal Adjustment into the Retail Trade Series (cat. no. 8514.0).
28 An improved correction method has been implemented in the seasonal adjustment process to remove the effects of Lunar New Year, Ramadan, Diwali and Easter from the seasonally adjusted estimates:
29 Seasonal adjustment procedures do not aim to remove the irregular or non-seasonal influences which may be present in any particular month, such as the effect of major sporting and cultural events, changes in airfares and the fluctuation of the Australian dollar relative to other currencies. Irregular influences that are highly volatile can make it difficult to interpret the underlying movement of the series even after adjustment for seasonal variation. Trend estimates take these irregular influences into account.
30 The trend estimates of short-term overseas visitor arrivals and short-term Australian resident returns are derived by applying a 13-term Henderson weighted moving average to all months of the respective seasonally adjusted series (after correcting the series for large extremes or changes in level) except the ends. A different set of specially designed Henderson moving averages are applied to the initial and last six months where the 13-term version cannot be used due to a lack of data points. While this technique enables smoothed data for the latest period to be produced, it does result in revisions to the smoothed series, principally of recent months, as additional observations become available. There may also be revisions as a result of the re-estimation of the seasonal factors. For further information, see A Guide to Interpreting Time Series - Monitoring Trends (cat. no. 1349.0) and Time Series Analysis Frequently Asked Questions, 2003 (cat. no. 1346.0.55.002).
31 Under concurrent seasonal adjustment, the most recent seasonally adjusted and trend estimates are likely to be revised when estimates for subsequent months become available. The trend revision is a combined result of the revision of the seasonally adjusted estimates and the revision derived from the use of asymmetric moving averages as future data become available. ABS research shows that about 75% of the total revision to the trend estimate is due to the use of different asymmetric moving averages when the estimate for the next time period becomes available. To assess the reliability of the trend estimate, the 'what-if' charts present trend estimates under two different scenarios for the next time period. The charts show only the impact due to the changes of the asymmetric moving averages and do not include the unknown impact of revision to seasonal factor estimates that would arise when the estimate for the next time period becomes available.
32 Occasionally situations occur that necessitate breaks being applied to the trend series. These breaks are necessary because of a change in the underlying level of the series. While the breaks apply to an individual country (e.g. Pakistan), a consequence is that breaks are also applied to the regional total series (e.g. Total Southern Asia) and the Total series.
33 Trend breaks currently included in the STVA and STRR trend series are as follows:
34 For a detailed discussion and analysis of OAD time series estimates, see the ABS Demography Working Paper 2004/2 - Interpretation and Use of Overseas Arrivals and Departures Estimates (cat. no. 3106.0.55.002).
35 For information looking at the implications of unusual external events on ABS time series, see the ABS Feature Article: When It's not "Business-as-usual": Implications for ABS Time Series (cat. no. 1350.0 for Aug 2009).
36 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.
37 Some techniques used to guard against identification or disclosure of confidential information in statistical tables are suppression of sensitive cells, random adjustments to cells with very small values and rounding. In these cases data may not sum to totals due to the confidentialisation of individual cells.
38 The statistics in this release have been rounded to the nearest 10 to maintain confidentiality. Where figures have been rounded, discrepancies may occur between sums of component items and totals. All calculations and analysis featured in this release are based on un-rounded data. Calculations made on rounded data may differ to those published.
ADDITIONAL STATISTICS AVAILABLE
39 The ABS may have other relevant data available on request. Generally, a charge is made for providing this information. Inquiries should be made to the National Information and Referral Service on 1300 135 070.
40 The following variables for overseas arrivals and departures data are available on request:
41 Related statistics are also published by:
42 As well as the statistics included in this and related releases, additional demographic information is available on the ABS website. Users can access the full range of electronic ABS data free of charge on the ABS website.
43 This release draws extensively on information provided by the Australian Government Department of Home Affairs and information provided by Services Australia. The ABS also uses 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.
These documents will be presented in a new window.