Australian Bureau of Statistics
3401.0 - Overseas Arrivals and Departures, Australia, Jan 2014 Quality Declaration
Previous ISSUE Released at 11:30 AM (CANBERRA TIME) 11/03/2014
|Page tools: Print Page Print All RSS Search this Product|
TAKE CARE! The estimates in this release have been revised back to July 2004 due to improved methodology used in the Overseas Arrivals and Departures system. See Rebuild of the Overseas Arrivals and Departures System below for details.
This release contains overseas movement data which should not be interpreted as 'persons'. See paragraph 7 of the Explanatory Notes for more detail.
The statistics in this release have been rounded. See paragraph 35 of the Explanatory Notes for more detail.
CHANGES IN THIS ISSUE
Please note, in 2013, the ABS completed a rebuild of the system which creates OAD data. With the rebuild of the OAD system all OAD data have been revised back to July 2004 based on an improved methodology. There is a break in series from July 2004. This month is the first release of the data based on the improved methodology.
For general information about the change see below — Rebuild of the Overseas Arrivals and Departures system. Detailed information on the changes and improvements appear in the Data Quality Issues section of this release, under the Explanatory Notes tab.
REBUILD OF THE OVERSEAS ARRIVALS AND DEPARTURES SYSTEM
The ABS has undertaken a rebuild of its Overseas Arrivals and Departures (OAD) system. The primary aim of this project was to improve the quality of OAD data, given its importance as an input to a broad range of statistical collections.
Why rebuild the OAD system?
OAD data is a key economic indicator, providing important information on cross-border movements. The data feeds into a number of important collections at the ABS including International Trade; National Income & Consumption; International Accounts and the Tourism Satellite Account. It is also a major input for estimating Net Overseas Migration (NOM) and therefore the Estimated Resident Population (ERP).
The data is also used extensively by other government departments, such as the Department of Immigration and Border Protection, and by business, particularly within the tourism industry.
The OAD system had not been reviewed in over 10 years and some assumptions and methodologies were in need of updating. The focus of the rebuild has been on improving the quality of OAD data through an enhanced processing methodology, with a particular emphasis on introducing more robust imputations for missing traveller data.
Through the process of the rebuild, all derivations, logical edits and imputations have been re-designed based on the best information, practices and methodology available at the time. All imputations within the new OAD system now use a hot deck imputation method. There are a number of imputations undertaken that specifically improve the quality of variables. These include country of stay, duration of stay, initial category of travel, passenger card box type, reason for journey and a specific one for the country of birth of New Zealand (NZ) citizens.
The specific imputation for country of birth of NZ citizens has improved country of birth statistics in the OAD, NOM, and ERP by country of birth collections. It has been introduced in the OAD collection for the first time with the release of the January 2014 OAD data and has been revised back to July 2004; for the NOM collection and the Travellers' Characteristics Database it has been revised back to December quarter 2003, and for the ERP collection by country of birth it has been revised back to 2006.
What data has changed?
Nearly all of the data has changed to some degree. The main variables that have changed due to the improved imputations include:
Update to country classification
Since October 2013 onwards, an excel spreadsheet outlining the country classification to be used with the improved OAD data has been available from the Data Cubes section under the Downloads tab. This country classification is based on the latest version of the Australian Standard Classification of Countries (SACC) 2011 Version 2.2 and has been introduced from 11 March 2014 onwards.
Has there been a break in series?
Yes, there has been a break in series from July 2004. With the rebuild of the OAD system all OAD data have been revised back to July 2004 based on the improved methodology.
When were the changes published?
The improved OAD data was made available from the reference month of January 2014 in Overseas Arrivals and Departures—Australia, January 2014 (cat. no. 3401.0), released on 11 March 2014.
A revised time series based on the improved methodology replaced all existing data for the reference period July 2004 to December 2013. Access to the previous time series remains available in Overseas Arrivals and Departures—Australia, December 2013 (cat. no. 3401.0).
Has this affected other ABS data?
Yes. All data that uses OAD data as a major input to their collection has been affected to some degree. Each area of the ABS, International Trade; National Income & Consumption; International Accounts and the Tourism Satellite Account provided their own additional information prior to the March 2014 OAD release.
Has this affected the NOM time series?
Yes. The data from the rebuilt OAD system has already been used to produce final NOM from September quarter 2006 onwards which has already been released in Australian Demographic Statistics, December Quarter 2012 (cat. no 3101.0). It made minimal change to the final NOM estimate, with analysis of the change included on page 22 of the same publication.
It has also affected preliminary NOM. The testing undertaken to date showed an improvement in accuracy for estimating preliminary NOM. Preliminary NOM data based on the improved OAD data became available from June Quarter 2013, in Australian Demographic Statistics, June Quarter 2013 (cat. no 3101.0) released on 17 December 2013.
An Information Paper: Further Improvements to Net Overseas Migration Estimation, Dec 2013 (cat. no. 3412.0.55.002) was also released on 17 December 2013.
Has this affected the Labour Force time series?
The impact on the Final NOM time series data is only marginal (i.e. generally less than 30 people), which in turn results in a similarly negligible impact on revisions to population estimates used to produce Labour Force Survey benchmarks. However, due to the rebuild there have been some small improvements to preliminary NOM estimates, which in turn results in small improvements to the quality of Labour Force Survey benchmarks. Historical Labour Force data will not be specifically revised as final NOM was not affected prior to 2011 and the small improvements after this time will be reflected in the regular rebenchmarking processes noted in 'Rebenchmarking in Labour Force Series' in Labour Force, Australia, Nov 2012 (cat. no. 6202.0).
Where do I look for more information?
Information on the improved methodology, particularly on the enhanced imputations, is available with the release of Overseas Arrivals and Departures—Australia, January 2014 (cat. no. 3401.0) release on 11 March 2014.
For further information about these and related statistics, contact the National Information and Referral Service on 1300 135 070 or Erica Galloway on Hobart (03) 6222 5884.
These documents will be presented in a new window.
This page last updated 4 April 2014