|Page tools: Print Page Print All|
Labour Statistics: Concepts, Sources and Methods was originally released in 2001 in both electronic and paper versions (cat. no. 6102.0). The paper publication will not be rereleased. However, the web version (cat. no. 6102.0.55.001) is being updated on an ongoing basis. This chapter was updated on 15 December, 2005.
33.4 Estimates can be cross classified by industry division and sub-division, and by business size.
33.5 Employment is defined in the survey as "the number of persons working for this business during the last pay period ending June" and includes: working proprietors; working partners; permanent, part-time, temporary and casual employees; managerial and executive employees; and employees absent on paid or pre-paid leave. Self employed persons are excluded. The definition of employment used in the survey is similar to that used in other ABS business surveys and excludes most self-employment jobs. See Chapter 3 for further information on the concept of employment, and on definitions of employment used in ABS household and business surveys.
SCOPE AND COVERAGE
33.6 The scope of the Economic Activity Survey is all employing businesses in the Australian economy except for:
97 Private Households Employing Staff;
33.7 Coverage of the survey varies in accordance with other specific industry collections being undertaken in the reference year. Thus, all units in Agriculture, Mining, Manufacturing, Electricity and Gas and some service industries were excluded from the Economic Activity Survey in respect of 1999-2000 to avoid duplication with other collections being undertaken in these industries for this reference year. In addition, data from the Australian Taxation Office and the Australian Prudential Regulation Authority are incorporated with directly collected data. The Australian Taxation Office data include information on non-employing businesses, details of which are not stored on the ABS Business Register.
33.8 A number of collection methods are used. Data for the units collected directly are obtained using a mail-out/mail-back collection methodology. This is supplemented by dropoff/pickup and telephone interviewing of selected units. Data are also obtained electronically from other ABS collections, and unit record data are obtained as administrative by-product data from the Australian Taxation Office and the Australian Prudential Regulation Authority.
33.9 The survey reference period is the year ending 30 June.
33.10 Businesses that do not respond by the due date are initially sent reminder letters and then followed up by telephone.
33.11 EAS uses a single stage stratified random sample which selects a sample of Management Units (MUs) from the ABS Business Register. The sample selections are undertaken using simple random sampling without replacement. The sample is controlled for overlap with past and future selections as well as with selections in other ABS economic surveys.
33.12 The frame is stratified by industry group and employment size of the management unit, whether the unit has been included as part of the survey groups for which ATO data are used, and whether the business is incorporated or unincorporated.
SAMPLE SIZE AND ALLOCATION
33.13 Data are collected directly from about 10,500 MUs. Data from an additional 7,500 units are collected in other ABS annual economic collections and then transferred to EAS. Data are also obtained for approximately 72,000 businesses from the ATO as a by-product of its data collection on business tax returns for the calculation of business income tax liability.
33.14 The sample design for the EAS collected units is based on achieving RSEs of 2% at the Australian level and averaging 6.5% at the sub-division level.
SAMPLE RE-SELECTION AND ROTATION
33.15 The EAS sample is re-selected every year. Where possible, small businesses (those with less than 20 employees) are rotated out of the survey after 3 years.
33.16 Number raised estimation is used.
33.17 Non-response is kept to a minimum by the use of intensive follow-up. Where possible, historical data are used for imputing non-responding units. Where units have not provided data previously or had not been selected in previous surveys Live Respondent Mean is used. Clerical imputation is used where only partial responses are received.
33.18 Survey outliers are treated using the 'surprise outlier' technique.
33.19 The estimation procedure includes new business provisions, which adjust estimates to allow for the time lag between businesses commencing operation and their inclusion on the ABS Business Register.
33.20 For further information on estimation methods used in ABS Business Surveys, refer to Chapter 25.
RELIABILITY OF THE ESTIMATES
33.22 Estimates from the survey are subject to both sampling and non-sampling error. The relative standard errors of survey estimates are published in Business Operations and Industry Performance, Australia (cat. no. 8140.0).
DATA COMPARABILITY OVER TIME
33.23 In order to provide a high degree of consistency and comparability over time, changes to survey methods, survey concepts, data item definitions, frequency of collection, and time series analysis methods are made as infrequently as possible. Significant changes have included:
33.24 For further details contact the Labour Market Statistics Section, on Canberra (02) 6252 7206.