Show download pdf controls
  • Reliability of the estimates

    The tax gap estimates are single-value (or point) estimates of a sample population and are subject to error. By their nature, tax gap estimates can have large margins of error which are difficult to precisely quantify. The International Monetary Fund advises 'there is a clear benefit in cautioning the audience about the inherent difficulties in providing precise point estimates, although margins of error themselves are not exact science either.1

    Errors can arise from the difference between the value obtained from source data used to estimate the gap, and the true value for the whole population. The data used in our tax gap estimates are affected by two types of error, which are defined by the Australian Bureau of Statistics (ABS), as follows:

    • Sampling error occurs solely as a result of using a sampleExternal Link from a population, rather than conducting a census (complete enumeration) of the population. It refers to the difference between an estimateExternal Link for a population based on data from a sample and the 'true' value for that population which would result if a censusExternal Link were taken.
    • Non-sampling error is caused by factors other than those related to sample selection. It refers to the presence of any factor, whether systemic or random, that results in the data values not accurately reflecting the 'true' value for the population. Non-sampling errors can occur at any stage of a census or sample study, and are not easily identified or quantifie quantified.2

    Additionally, changes in the gap estimates from year to year could be due to real movements in compliance or they could be spurious in nature. This means greater reliance should be placed on the trend in the tax gap rather than the point estimate for any one year.

    Assessing the performance of the tax system, including taxpayer compliance and our administration, requires consideration of all our performance indicators, rather than the tax gap estimates in isolation.

      Last modified: 05 Nov 2015QC 47278