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.
28.4 Costs are measured on a cash accounting basis, net of any reimbursements, subsidies or rebates. 28.5 Data can be classified by State or Territory, sector (public/private), level of government, public institutional sector, industry and employer size. The following units of measure are available: total costs; costs per employee; and costs as a proportion of total labour costs. 28.6 Data from the survey are available on an original basis only. 28.7 Data collected in the survey are compiled according to concepts and definitions outlined in Chapter 12. All labour costs are collected on a cash basis i.e. they reflect actual payments made in the survey reference period. As such they do not reflect costs incurred in the reference period for which payments are made in a later period, but they include payments made in the survey reference period for costs incurred in a prior period. 28.8 Earnings estimates from the survey are broader than, and thus not directly comparable with, earnings estimates from the Survey of Average Weekly Earnings (AWE), and the Survey of Employee Earnings and Hours (EEH). For more details on the earnings definition in MLC, see Chapter 12. 28.9 A number of other labour costs are not covered by this survey. These include training costs, costs associated with employee welfare services, and recruitment costs. With the exception of training costs, these items are not considered to make a significant contribution to total labour costs. Training costs were collected in the Training Expenditure and Practices Survey, conducted for the financial year 2001-02, and in the earlier Training Expenditure Survey conducted for September quarters of 1989, 1990, 1993 and 1996. Costs covered in these surveys are for structured training provided by employers. For information see Employer Training Expenditure and Practices, Australia (cat. no. 6362.0). SCOPE 28.10 The scope of the survey is restricted to employing organisations in Australia. The standard scope exclusions for ABS labour-related business surveys (outlined in Chapter 25)apply to this survey. SURVEY METHODOLOGY 28.11 Detailed information is obtained about labour costs from selected employers using a mail-out/mail-back collection methodology. 28.12 The survey reference period is the financial year ended 30 June. 28.14 Respondents who do not mail back their completed questionnaire within a reasonable period of time after the survey reference date are followed up by mail and then telephoned if necessary. The response rate for the 2002-03 survey was 93%. SAMPLE DESIGN 28.15 The sampling unit for the survey comprises all the activities of an employer in a particular state or territory based on the Australian Business Number (ABN) unit or Type of Activity Unit (TAU). The collection and reporting units used in the survey usually correspond to the sampling unit. However, where the ABN/TAU unit is unable to provide information required for the survey, it may be split into a number of 'reporting units'. For further information on statistical units used in ABS business surveys refer to Chapter 25. 28.16 A probability sample of employing businesses (ABN/TAU units) is drawn from the ABS Business Register using the process outlined in Chapter 25. Variables used to stratify the survey frame are:
28.17 A Workers' Compensation Insurer type identifier was unavailable for inclusion in the initial stratification, but the sample was effectively post stratified for this classification (re-weighting for workers' compensation data items only) during output processing. 28.18 Strata on the survey frame that are completely enumerated include those containing selection units with benchmark employment greater than a set cut-off (this cut-off will vary for different states/territories) and strata with a very small number of selection units in the population. 28.19 In addition to constraints outlined in Chapter 25, sample selection is constrained by ensuring there is minimum overlap with other labour-related business surveys. SAMPLE SIZE AND ALLOCATION 28.20 For the 2002-03 survey, approximately 7,500 employer units were selected to ensure adequate industry and state/territory representation. Of these, approximately 5,600 units were in the private sector and 1,900 were in the public sector. SAMPLE RESELECTION 28.21 The ABS reselects the sample for the Survey of Major Labour Costs each time it is conducted. At the same time the overall design of the sample is examined to ensure that it remains efficient and cost-effective. ESTIMATION 28.22 Both ratio estimation and number-raised estimation (for some strata) are used. 28.22 Survey outliers are handled by using the 'surprise outlier' technique. 28.23 Aggregate Ratio imputation is applied to all non-responding units that are not identified as being defunct. The unit is imputed by applying the aggregate ratio of each item to benchmark from respondent units of a similar type (e.g state, industry, size, not-for-profit status, workers' compensation arrangement) as relevant to each item. 28.24 Partial clerical imputation is carried out for units that can only provide part data. The missing item(s) is imputed using the relationship between that item and a relevant provided item as per responding units of similar type. Where relevant and available, employment and earnings data obtained from the SEE or AWE survey are used to assist clerical imputation. 28.25 Adjustments are made to survey estimates to account for births and deaths of businesses that have occurred up to the end of the survey reference period but which are not reflected on the survey frame. 28.26 For further information on estimation methods used in ABS Business Surveys, refer to Chapter 25. RELIABILITY OF THE ESTIMATES 28.27 Estimates from the survey are subject to both sampling and non-sampling error. The relative standard errors of survey estimates are published in Labour Costs, Australia (cat. no. 6348.0.55.001). 28.28 The 'jack-knife' approach is used to calculate estimates of variance for this survey. For further information on variance estimation techniques, or on sampling and non-sampling error, refer to Chapter 17. DATA COMPARABILITY OVER TIME 28.29 In order to provide a high degree of consistency and comparability over time, changes to survey methods, survey concepts, data item definitions, and frequency of collection, are made as infrequently as possible. Significant changes have included:
28.30 Although many estimates from previous collection cycles are on a consistent basis, care should be taken in using data from this survey as a time series. The survey is designed to give an accurate 'snapshot' of data rather than an ongoing series of observations over time. Hence the survey methodology and sample design are not specifically set up to provide time series data e.g. the sample is not set up to necessarily have the same businesses in it for more than one year. Also changes in definitions and treatments for data items can occur, as for the 2002-03 survey. The Explanatory Notes of the publication provides detail on such changes. FURTHER INFORMATION 28.31 For further details contact the Labour Market Statistics Section, on Canberra (02) 6252 7206.
|