Since the estimates for private sector and public sector organisations are based on a sample of organisations they are subject to sampling error; that is, they may differ from the figures that would have been obtained if information for all organisations for the relevant period had been included in the survey. A measure of the likely difference is given by the relative standard error (RSE) of each estimate. There are about 2 chances in 3 that a sample estimate will differ by less than one standard error from the figure that would have been obtained if all units had been included, and about 19 chances in 20 that the difference will be less than 2 standard errors. Approximate RSEs of the estimates can be found in datacubes under 'data downloads'.
An example of the use of RSEs is as follows. If the total value of work done during the quarter is $2,500m and the associated RSE is 0.5% then there are about 2 chances in 3 that the value which would have been obtained if there had been a complete collection would have been within the range $2,488m to $2,513m and about 19 chances in 20 that the value would have been within the range $2,475m to $2,525m.
Estimates that have an estimated relative standard error between 10% and 25% are annotated with the symbol ‘^’. These estimates should be used with caution as they are subject to sampling variability too high for some purposes. Estimates with an RSE between 25% and 50% are annotated with the symbol ‘*’, indicating that the estimate should be used with caution as it is subject to sampling variability too high for most practical purposes. Estimates with an RSE greater than 50% are annotated with the symbol ‘**’ indicating that the sampling variability causes the estimates to be considered too unreliable for general use.
The imprecision due to sampling variability, which is measured by the RSE, should not be confused with inaccuracies that may occur because of inadequacies in the source of information, imperfections in reporting by respondents, and errors made in the coding and processing of data. Inaccuracies of this kind are referred to as non-sampling error, and may occur in any enumeration whether it be a full count or only a sample. Every effort is made to reduce the non-sampling error to a minimum by the careful design of questionnaires, efforts to obtain responses for all selected organisations, and efficient operating procedures.
Caution is advised in respect of the value of work commenced (and consequently, the value of work yet to be done) reported by the public sector. It is known that data reported for value of work commenced are a combination of the following: annual works budget estimates which are reported as commencements in the September quarter (and in some cases may subsequently be undertaken by the private sector); genuine commencements as defined in the Glossary, and reported quarterly; commencements being reported as equal to the value of work done for the quarter; commencements of major stages in the case of long-term projects.
Revisions are made to the survey data as required as a result of new and updated information available from providers. Generally revisions are confined to the last 2-3 quarters.