TECHNICAL NOTE 2 DATA QUALITY

Quality indicators

Data comparability


RELIABILITY

1 The estimates in this release are based on information obtained from a sample survey (i.e. EAS Community Services) conducted by the Australian Bureau of Statistics (ABS). Any collection of data can be affected by factors that affect the reliability of the resulting statistics, regardless of the methodology used. These factors result in non-sampling error. In addition to non-sampling error, sample surveys are also subject to inaccuracies that arise from the fact that a sample was selected rather than conducting a census. This type of error is called sampling error.


Sampling error

2 Sampling variability occurs when a sample, rather than the 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 likely difference is given by the standard error, which indicates the extent to which an estimate might have varied by chance because only a sample of units was included.

3 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 19 chances in 20 that the difference will be less than two standard errors.

4 Another measure of sampling variability is the relative standard error (RSE), which is obtained by expressing the standard error as a percentage of the estimate to which it refers. The RSE is a useful measure in that it provides an immediate indication of the sampling error in percentage terms, and this avoids the need to refer also to the size of the estimate. Selected data item RSEs at the aggregate level for Australia are shown in the table overleaf. Detailed relative standard errors can be made available on request.

Relative Standard errors for key aggregates
		For profit organisations(a)	Not-for-profit organisations(a)	Commonwealth/ state/territory government	Local government	Total
		%	%	%	%	%
Businesses/organisations providing community services at end June		1.6	1.4	-	2.0	0.9
Employment at end June
	Direct community services provision	1.8	0.9	-	1.6	0.6
	Non-direct/other	4.3	1.9	-	1.8	1.5
	Total	1.7	0.7	-	1.5	0.5
Volunteers during the year		np	4.9	. .	np	4.4
Expenditure on direct community services activities
	Personal and social support	9.0	1.7	-	1.7	1.2
	Child care	2.2	2.8	np	np	1.5
	Training and employment for persons with disabilities	0.1	3.4	. .	. .	2.7
	Financial and material assistance	1.0	9.8	-	. .	7.4
	Residential care	2.7	1.4	-	4.4	1.0
	Foster care placement	7.9	3.6	-	. .	1.6
	Accommodation placement and support	25.3	7.0	np	np	5.2
	Statutory protection and placement	8.0	6.7	-	. .	0.5
	Juvenile/disability detention and corrective services	32.4	22.0	-	. .	0.8
	Total	1.8	0.9	-	1.6	0.6
Expenditure on non-direct community services activities		6.4	3.0	-	2.3	1.5
Funding and payments to other organisations and self-employed contractors for the direct provision of community services		7.3	4.4	-	2.8	0.3
. . not applicable
- nil or rounded to zero (including null cells)
np not available for publication but included in totals where applicable, unless otherwise indicated
(a) Includes government trading enterprises.

5 To illustrate the above, the estimate of total expenditure on direct community services activities in 2008-09 was $25,184.9m. The RSE of this estimate is shown as 0.6%, giving a standard error of approximately $151.1m. Therefore, there are two chances in three that, if all units had been included in the survey, an estimate in the range of $25,033.8m to $25,336.0m would have been obtained. Similarly, it implies that there are nineteen chances in twenty (i.e. a confidence interval of 95%) that the estimate would have been within the range of $24,882.7m to $25,487.1m.

6 The size of the RSE may be a misleading indicator of the reliability of some of the estimates for (a) operating profit before tax and (b) industry value added. It is possible for an estimate legitimately to include positive and negative values, reflecting the financial performance of individual businesses/organisations. In this case, the aggregated estimate can be small relative to the contribution of individual businesses/organisations, resulting in a standard error which is large relative to the estimate.


Non-sampling error

7 Error other than that due to sampling may occur in any type of collection, whether a full census or a sample, and is referred to as non-sampling error. It can arise from inadequacies in available sources from which the population frame was compiled, imperfections in reporting by providers, errors made in collection such as in recording and coding data and errors made in processing data. It also occurs when information cannot be obtained from all businesses selected.

8 Although it is not possible to quantify non-sampling error, every effort was made to reduce it to a minimum. Collection forms were designed to be easy to complete and assist businesses to report accurately. Efficient and effective operating procedures and systems were used to compile the statistics. The ABS compared data from different ABS (and non-ABS) sources relating to the one industry, to ensure consistency and coherence.

9 Differences in accounting policy and practices across businesses and industries can lead to some inconsistencies in the data used to compile the estimates. Although much of the accounting process is subject to standards, there remains a great deal of flexibility available to individual businesses in the accounting policies and practices that they adopt.

10 The above limitations are not meant to imply that analysis based on these data should be avoided, only that the limitations should be borne in mind when interpreting the data presented in this publication. This publication presents a wide range of data that can be used to analyse business and industry performance. It is important that any analysis be based upon the range of data presented rather than focusing on one variable.


QUALITY INDICATORS

11 In the 2008-09 survey of community services, there was a 91% response rate from all businesses that were surveyed and found to be operating during the reference period. Data were imputed for the remaining 9% of operating businesses. Imputed responses contributed 4.5% to the estimate of total income for all selected industries.

DATA COMPARABILITY

Comparison with other ABS statistics

Australian Industry (cat no. 8155.0)

12 Key annual industry data for ANZSIC06 subdivisions 86 Residential care services and 87 Social assistance services are published in Australian Industry (cat. no. 8155.0). There are important differences between statistics published in Australian Industry and Community Services and users should exercise caution when making comparisons between the two sets of estimates. A key difference is the inclusion of micro non-employers in Australian Industry, where they contribute less than 2% to total turnover in subdivision 86 and less than 2.25% in subdivision 87.

13 Australian Industry presents annual summary statistics at the ANZSIC06 division and subdivision levels. It shows the relative performance of each industry division and subdivision, and allows patterns of change of growth to be analysed across particular segments of the Australian economy.

14 Community Services supplements Australian Industry statistics with a detailed examination of the structure and performance of community services businesses/organisations for the reference year of the survey. As such, the survey is not designed to monitor change over time.

Counts of Australian Businesses, including Entries and Exits (cat. no. 8165.0)

15 Estimates of the number of businesses operating in Australia can be derived from a number of sources within the ABS. They may relate to a particular point in time or may be presented as an average annual figure. However, these estimates will not always show the same results. Variations will occur because of differing data sources, differing scope and coverage definitions between surveys, as well as variations due to sampling and non-sampling error. More information about business counts can be found in the information paper A Statistical View of Counts of Businesses in Australia (cat. no. 8162.0).

16 The Community Services survey is not designed to provide high quality estimates of numbers of businesses for any of the output classifications (for example, employment size or industry) and the number of businesses in this publication are only included to provide contextual information for the user. A more robust source of counts of Australian businesses is available from Counts of Australian Businesses, including Entries and Exits, Jun 2003 to Jun 2007 (cat. no. 8165.0)

Not-for-profit organisations (cat. no. 8106.0)

17 Selected data on the 'not for profit' sector is published in Not-for-profit Organisations (cat. no. 8106). The classification system used in this survey was a reduced version of the International Classification of Non-Profit Organisations. Whilst this allows a fuller specification of the components of the not-for-profit sector, it does not have a concordance which enables a ready comparison to ANZSIC06, upon which this survey is based.

Historical comparisons

18 The reader should bear in mind that this survey was not designed to support accurate estimates of change over time. There have been major changes in the statistical units, frame, scope, industry classification and estimation methodology between the 1999-2000 and 2008-09 Community Services surveys. These include:

• changes to the statistical unit as a result of the introduction of The New Tax System on 1 July 2000
• changes to the frame as a result of drawing information from the ATO ABR into the ABSBR
• changes to scope as a result of including significant non-employing units in the survey
• major changes between the 1993 and 2006 editions of ANZSIC which affected all community services sectors
• the introduction of generalised regression estimation methodology instead of number raised estimation.

19 Consequently, estimates in this issue are not directly comparable with those in the 1999-2000 issue and users are advised against making historical comparisons.