|Page tools: Print Page Print All|
QUALITY DECLARATION - SUMMARY
The ABS aims to produce high quality data from its industry collections while minimising the reporting burden on businesses. To achieve this, extensive effort is put into survey and questionnaire design, collection procedures and processing. Estimates from the survey are compiled using generalised regression, a form of ratio estimation which makes use of auxiliary data items which are strongly correlated with key data items directly collected by the ABS from businesses. The auxiliary variables used in this survey were turnover and wages from data sourced from the ATO. Use of this methodology allowed high quality statistics to be produced from a small, direct collect sample of 1,116 businesses.
Two types of error can occur in estimates that are based on a sample survey, sampling error and non-sampling error.
Sampling error occurs when a sample, rather than an entire population is surveyed. It reflects the difference between estimates based on a sample and those that would have been obtained had a census been conducted. One measure of the difference is standard error. There are about two chances in three that a sample estimate will differ by less than one standard error from the figure that would have been obtained if all businesses had been included in the survey, and about nineteen chances in twenty that the difference will be less than two standard errors.
Another measure of sample error is the relative standard error, which is obtained by expressing the standard error as a percentage of the estimate to which it refers. The relative standard error is a useful measure in that it provides an immediate indication of the sampling error in percentage terms, avoiding the need to refer also to the size of the estimate. Relative standard errors of key estimates are available in the Technical note on Data Quality of this publication.
Non-sampling error arises from inaccuracies in collecting, recording and processing the data. Every effort was made to minimise reporting error, by the careful design of questionnaires, intensive training of survey analysts, and efficient data processing procedures.
Non-sampling error also occurs when information cannot be obtained from all businesses selected in the survey. The IMT component of the EAS survey had an 86.9% response rate from all businesses that were surveyed and found to be operating during the reference period. Data was imputed for the remaining businesses. This imputation contributed 2.5% to the sales and service income estimates presented in this publication.
The Australian Bureau of Statistics conducts an Economic Activity Survey each year. The standard questionnaire collects information on a range of indicators including employment, income, expenses and capital expenditure. The definitions of these are reviewed each year and are refined or re-specified as needed. Additional data items are collected in different years, in response to demand and priorities.
The survey collects more detailed information from a range of industries which vary from year to year. Additional information was collected for the Information Media and Telecommunications industry for 2013-14. The estimates presented in this publication are compiled on the same basis as those presented in Australian Industry (cat. no. 8155.0).
Estimates released in this publication are available as original series only.
Although financial estimates in this release relate to the full twelve months, employment estimates relate to the last pay period ending in June 2014.
Further information about terminology and other technical aspects associated with these statistics can be found in the detailed Explanatory Notes, a Technical Note on Estimation Methodology, a Technical Note on Data Quality and a Glossary.
Data from the survey are available free of charge on the ABS website.
These documents will be presented in a new window.