|Page tools: Print Page Print All|
QUALITY DECLARATION – PRELIMINARY OVERSEAS ARRIVALS AND DEPARTURES, AUSTRALIA
Preliminary OAD data provides information on all recorded movements across Australia's borders, both in-bound and out-bound, by category of movement by each state or territory of residence/stay. The three main categories of movement are:
These data provide input into various macroeconomic accounts in estimating imports and exports of travel services, including air transport imports, education travel exports and household expenditure on travel services, and components of compensation of employees. They are also of relevance to international tourism research.
Geographically, preliminary OAD data are available at the Australia and state and territory levels.
Care should be taken when interpreting OAD movement data as 'people' as these statistics 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 statistics exclude 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 unauthorised arrivals. Users requiring data on the number of travellers (people) who stay within (or away from) Australia for at least 12 months may find NOM estimates more suitable to meet their needs. For more information on NOM see the Explanatory Notes in Migration, Australia (cat. no. 3412.0).
Preliminary OAD statistics are to be released quarterly until the delay in release of Overseas Arrivals and Departures, Australia (cat. no. 3401.0) has resumed its normal monthly schedule. For the revised release schedule please see the Notes section of this release.
The Preliminary OAD statistics are modelled using a one-year-ago propensity for passenger card data relative to movement data stored on TRIPS. The TRIPS movement data are the most up-to-date source available and is a strongly correlated data source compiled from administrative records such as passport scans and visa information that is managed by DIBP.
The one-year-ago propensity is calculated separately for each month of the year, using only matching months from past years, eg model for the current October based on the previous October one-year-ago. This ensures that the model reflects the seasonal patterns in OAD data. Key TRIPS variables such as Direction (Arrivals or Departures) and Visa type were used as correlates in the model to improve accuracy. The addition of correlates in the model, such as visa type, was done by estimating propensities and modelling card counts by a subgrouping. Aggregating across those subgroups was the final step in producing the model predictions.
For an estimate of accuracy, users can refer to the relative root mean square error (RRMSE) which can be used in a similar fashion to a relative standard error would be for sample surveys. The RRMSE is an estimate of accuracy for the modelled values, based on how well the model performs in comparison with known historical data. For further information see Explanatory Notes 7 to 13.
The data available with this release is preliminary OAD and has been modelled. It is broadly comparable with the standard final OAD data series associated with Overseas Arrivals and Departures, Australia (cat. no. 3401.0).
OAD data measure crossings of Australia's borders. Final OAD data are available from 1901, for various categories of traveller (e.g. permanent, long-term and short-term arrivals and departures) and periods (e.g. annual, quarterly and monthly). Electronic data are available from Overseas Arrivals and Departures, Australia (cat. no. 3401.0) for categories of traveller on a monthly basis from January 1976, with selected variables available from January 1991.
To provide a high degree of consistency and comparability over time, this administrative data has required careful and continuing maintenance and development to protect the integrity of the data and the efficiency of the collection. Changes that have occurred over the collection period include: sampling methods, estimation methods, concepts, data item definitions, classifications, time series analysis techniques and modelling. For example the change in boundaries and existence of various countries can affect their comparability over time.
All preliminary OAD data are original series estimates (as opposed to seasonally adjusted or trend estimates). Care should be taken by users as these preliminary estimates are modelled. The model relies upon seasonal and trend behaviour remaining consistent with recent history up to September 2014.
Further information can be obtained from the Explanatory Notes and Appendixes in this publication.
Preliminary OAD data are a web-only release with two associated time series spreadsheets (Excel format) available from the Downloads tab.
These documents will be presented in a new window.