TECHNICAL NOTE 1 METHODOLOGY


INTRODUCTION

1 The industry estimates in this publication are produced using a combination of ABS directly collected data and Business Activity Statement (BAS) tax data sourced from the Australian Taxation Office (ATO).

2 The directly collected data have been reported by a sample of manufacturing businesses, as recorded on the ABS Business Register (ABSBR). The ABS uses an economic statistics units model on the ABSBR to describe the characteristics of businesses, and the structural relationships between related businesses. Within large and diverse business groups, the units model is used also to define reporting units that can provide data to the ABS at suitable levels of detail.


STATISTICAL UNITS DEFINED ON THE ABS BUSINESS REGISTER

3 The current economic statistics units model was introduced in mid 2002, to better use the information available as a result of The New Tax System (TNTS). This units model allocates businesses to one of two sub-populations. The vast majority of businesses are in what is called the ATO maintained population, while the remaining businesses are in the ABS maintained population. Together, these two sub-populations make up the ABSBR population.


ATO MAINTAINED POPULATION

4 Most businesses and organisations in Australia need to obtain an Australian Business Number (ABN). They are then included on the whole-of-government register of businesses, the Australian Business Register (ABR), which is maintained by the ATO. Most of these businesses have simple structures; therefore, the unit registered for an ABN will satisfy ABS statistical requirements. For these businesses, the ABS has aligned its statistical units structure with the ABN unit. The businesses with simple structures constitute the ATO maintained population, and the ABN unit is used as the statistical unit for all ABS economic collections.


ABS MAINTAINED POPULATION

5 For the population of businesses where the ABN unit is not suitable for ABS statistical requirements, the ABS maintains its own units structure through direct contact with the business. These businesses constitute the ABS maintained population. This population consists typically of large, complex and diverse businesses. The statistical units model described below caters for such businesses.

Enterprise group: This is a unit covering all the operations in Australia of one or more legal entities under common ownership and/or control. It covers all the operations in Australia of legal entities which are related in terms of the current Corporations Law (as amended by the Corporations Legislation Amendment Act 1991), including legal entities such as companies, trusts and partnerships. Majority ownership is not required for control to be exercised.

Enterprise: An institutional unit comprising:

(i) a single legal entity or business entity, or

(ii) more than one legal entity or business entity within the same enterprise group and in the same institutional sub-sector (i.e. they are all classified to a single Standard Institutional Sector Classification of Australia (SISCA) sub-sector).

Type of activity unit (TAU): The TAU comprises one or more business entities, sub-entities or branches of a business entity within an enterprise group that can report production and employment data for similar economic activities. When a minimum set of data items are available, a TAU is created which covers all the operations within an industry subdivision (and the TAU is classified to the relevant subdivision of the ANZSIC). Where a business cannot supply adequate data for each industry, a TAU is formed which contains activity in more than one industry subdivision.


CONTRIBUTION OF THE STATISTICAL UNITS TO THE ESTIMATES

6 TAUs: All units in the ABS maintained population (i.e. TAUs) classified to manufacturing were eligible to be selected for direct collection. Direct collection of data from these units is necessary because:

• many large and complex employing businesses have more than one legal entity, making it difficult to identify all legal entities for that business in the BAS data.
• BAS data do not include all of the detailed information that the ABS requires from large and complex businesses
• 'tax exempt' businesses that are not required to complete business income tax returns would otherwise not contribute to the statistics.

7 ABN units: The balance of units on the ABSBR classified to manufacturing were ABN units, from the ATO maintained population.

8 An indication of the importance of these populations to the data can be gained from their contribution to the national estimate of sales and service income for Total Manufacturing. The following table shows their proportional contributions to sales and service income.

Contribution to sales and service income
	TAU	ABN unit	Total
	%	%	%
11 Food product mfg	72	28	100
12 Beverage and tobacco product mfg	86	14	100
13 Textile, leather, clothing and footwear mfg	28	72	100
14 Wood product mfg	47	53	100
15 Pulp, paper and converted paper product mfg	78	22	100
16 Printing (including the reproduction of recorded media)	40	60	100
17 Petroleum and coal product mfg	97	3	100
18 Basic chemical and chemical product mfg	76	24	100
19 Polymer product and rubber product mfg	52	49	100
20 Non-metallic mineral product mfg	70	30	100
21 Primary metal and metal product mfg	92	8	100
22 Fabricated metal product mfg	39	61	100
23 Transport equipment mfg	71	29	100
24 Machinery and equipment mfg	43	57	100
25 Furniture and other mfg	14	86	100
11-25 Total manufacturing	69	31	100

COLLECTION DESIGN

9 In order to decrease the statistical reporting load placed on providers while maintaining the range and quality of information available to users of statistical data, the strategy for this survey was to adopt the use of directly collected data from a smaller sample of businesses, in combination with information sourced from the ATO. The frame (from which the direct collect sample was selected) was stratified using information held on the ABS Business Register. Businesses eligible for selection in the direct collect sample were then selected from the frame using stratified random sampling techniques.

10 Businesses were selected to participate in the survey (the direct collect sample) only if they met two criteria: their turnover exceeded a threshold level and the business was identified as having been an employing business (based on ATO information) during the reference period. Turnover thresholds were set for each ANZSIC class so that the contribution of surveyed businesses accounted for 97.5% of total industry class turnover as determined by ATO Business Activity Statement data.

11 Businesses which met neither of these criteria are referred to as 'micro non-employing businesses'. These businesses were not eligible for selection in the sample. For these units, BAS data were obtained and annualised, then added to the directly collected estimates to produce the statistics in this publication. The total estimated value of annual turnover of micro non-employing manufacturing businesses during the 2006-07 reference year, as determined by ATO Business Activity Statement data, was $2.5b.


ESTIMATION METHODOLOGY

12 Estimates from previous iterations of this survey were produced using number raised estimation methodology. The 2006-07 survey used generalised regression estimation.This estimation method enables maximum use of observed linear relationships between data directly collected from businesses in the survey and auxiliary information. When the auxiliary information is strongly correlated with data items collected in a survey, the generalised regression estimation methodology will improve the accuracy of the estimates. The auxiliary variables used in this survey were turnover and wages sourced from ATO Business Activity Statement data.


PRODUCING ESTIMATES

13 The following diagram illustrates the ways in which Australian businesses contribute to the estimates in this publication.

DATA STREAMING

14 For the purpose of compiling the estimates in this publication, data for businesses as recorded on the ABSBR contribute via one of three categories (or 'streams') in accordance with significance and collection-related characteristics.


Completely Enumerated (CE) Stream:

15 The CE stream consists of directly collected survey data for those units recorded on the ABSBR as having employment greater than 300, plus additional 'significant' units in the ABS maintained population and units significant to small state estimates.


Generalised regression (GREG) estimation Stream:

16 The GREG stream comprises directly collected data for those sampled units which are not in the CE stream and have turnover, in aggregate, above the bottom 2.5 percentile of BAS sales for that industry. The accuracy of the estimates produced from this data is then improved by using wages and turnover data sourced from businesses' BAS data.


Business Activity Statement (BAS) Stream:

17 The BAS stream comprises data for those businesses in the ATO maintained population whose turnover, in aggregate, is below the bottom 2.5 percentile of BAS sales for that industry.

18 Estimates for each of the selected industries were produced by aggregating the contributing data streams.


STATE ESTIMATES

19 Estimates of state data in this survey were produced using data from pre-identified sample selections that operated in more than one state. All other sampled units had all their reported data allocated to their main state of operation.


EMPLOYMENT ESTIMATES

20 One implication of the use of BAS data in these statistics is that no direct measure of employment is available for those units which contribute to the estimates solely through the BAS source. This is because the ATO does not collect information about employment numbers. Unlike financial variables, which have a direct relationship to the data available from the BAS files, employment data are not amenable to being modelled using the same techniques. Hence a different methodology is used in order to estimate employment for those units whose data are sourced solely from the BAS files. For each such business, the number of employees is assumed to be zero. For each unincorporated business an estimate of its number of working proprietors or partners is used as the estimate of its total employment. These estimates are then aggregated to the directly collected data to produce the estimates in this publication.


EMPLOYMENT SIZE ESTIMATES

21 For consistency, employment size estimates in table 2.3 have been presented using identical size categories as in previous issues. A result of the methodological changes introduced in 2006-07 is that the stratification boundaries no longer align as closely with these size ranges. The cut off for completely enumerated (CE) businesses was for any business with employment of 50 or more persons. This meant that employment size categories for 50 and above persons employed were CE'd and had the associated level of precision. The cut off for CE'd units in the 2006-07 survey was units with employment of 300 or more persons which meant sampling variability was introduced for units above 49 persons employed that was not present before. The sample stratification boundaries for sampled units also changed in 2006-07 and the correlation to existing size boundaries is not as strong as in previous years. As a consequence the relative standard errors (RSE) for employment size will be higher than previously. The RSE's can be made available on request.


HISTORICAL ESTIMATES

22 Data collected for 2004-05 and 2005-06 (under ANZSIC93) have been updated to take account of any revisions to the data since they were published in the previous issue of this publication. The data so revised have then been mapped to ANZSIC06, and further adjusted to incorporate the scope changes outlined in Explanatory Notes paragraph 9 and the methodological changes discussed in this chapter. This process is known as 'bridging' and was used to create the key data items presented in Table 1.1.