TECHNICAL NOTE DATA QUALITY
NON-SAMPLING ERROR
1 Non-sampling errors may arise as a result of errors in the reporting, recording or processing of data. These errors can be introduced through inadequacies in the questionnaire, treatment of non-response, inaccurate reporting by data providers, errors in the application of survey procedures, incorrect recording of answers and errors in data capture and processing.
2 The extent to which non-sampling error affects the results is difficult to measure. Every effort is made to minimise non-sampling error by careful design and testing of the collection instrument, the use of efficient operating procedures and systems, and the use of appropriate methodologies.
Reliability of statistics
3 When interpreting the statistics in this release, the reliability and comparability of the estimates may be affected by the following specific non-sampling errors:
- Many businesses provided estimates due to a lack of separately recorded data on R&D activity.
- Some businesses may not have reported data as per the definition of R&D used in this survey. This is potentially a result of slight differences in the survey definition of R&D and those used in industry R&D schemes for the allocation of grants, and the AusIndustry administered R&D Tax Concession scheme for tax deductibility for specific R&D activities.
- Data were self-classified by businesses to Type of activity, Fields of research and Socio-economic objective at the time of reporting. Some businesses may have experienced difficulty in classifying their R&D projects. The ABS makes every effort to ensure correct and consistent interpretation and reporting of these data by applying consistent processing methodologies.
- The estimation method for R&D related overhead costs varied across businesses and reference periods.
Comparability of estimates over time
4 The comparability of estimates over time may be affected by the following changes in classifications:
- Employment size classification groups are defined on data reported in the reference period, and as such businesses may be categorised to different employment size groups across different reference periods.
- Businesses can also be classified to different industry divisions across survey reference periods as a consequence of structural change. See paragraphs 23 and 24 of the Explanatory Notes for more information.
Treatment of non-response
5 For non-responding businesses that had reported R&D activity in the 2009-10 survey, data for 2010-11 were imputed using previous cycle data.
6 For non-responding businesses that did not report R&D activity in the previous cycle, data were not imputed. These businesses are not expected to have significant levels of R&D activity.
REVISIONS
7 Revisions to previous cycle data occur on discovery of:
- errors in reported data, typically a result of the specific non-sampling errors outlined in the Reliability of Statistics section above; and
- newly identified R&D performers who indicated they had significant levels of R&D in earlier years (details are collected and used to revise previously released estimates).
8 Revisions are applied up to two cycles prior to the current cycle, but only where the impact on:
- R&D expenditure is equal to $5 million or more;
- Human resources devoted to R&D is equal to 25 PYE or more; or
- Published level data is of proportional significance.
9 In processing 2010-11 data, revisions were applied to 2008-09 and 2009-10 estimates. Revisions must be taken into consideration when interpreting results, particularly when comparing estimates over time.