Methods

Crude rates

A crude rate is defined as the number of events over a specified period (for example, a year) divided by the total population at risk of the event.

Age-specific rates

An age-specific rate is defined as the number of events for a specified age group over a specified period (for example, a year) divided by the total population at risk of the event in that age group. Unless otherwise stated, rates presented throughout this report are age-specific.

Age-specific rates in this report were calculated by dividing, for example, the number of events (for example, hospital separations or deaths, new cases of cancer) in each specified age group by the corresponding population in the same age group.

Age-standardised rates

Age-standardised rates enable comparisons to be made between populations that have different age structures. Direct standardisation was used in this report, in which the age-specific rates are multiplied by a constant population. This effectively removes the influence of the age structure on the summary rate. Where age-standardised rates have been used, this is stated throughout the report.

All age-standardised rates in this report have used the June 2001 Australian total estimated resident population as the standard population.

Confidence intervals

The observed value of a rate may vary due to chance even where there is no variation in the underlying value of the rate. Therefore, where measures based on survey data include a comparison between time periods, geographical locations, socioeconomic groups, country of birth or disability status, 95% confidence intervals have been calculated. The confidence intervals are used to provide an approximation indication of the true differences between rates. They are shown on graphs as error bars. If the error bars do not overlap, the difference can be said to be statistically significant. However, in some instances where the confidence intervals (and error bars) overlap only slightly, a further significance test (using the z-test) can indicate a statistically significant difference. Where differences were found to be statistically significant, they are noted in the text.

However, statistically significant differences are not necessarily the same as differences considered to be of practical importance. It is possible for small differences that have practical importance to be found to be not statistically significant as they are below the threshold the significance test can reliably detect.

Data subject to revision

This report draws data from a range of administrative and survey data sets, all of which are subject to change. Such changes may arise from:

  • the nature and timing of the data collection—for example, notifiable diseases are based on a ‘real-time’ collection of reported cases, and the counts and rates could change daily
  • a regular program of updates and maintenance—for example, for 2007 data onwards, the Australian Bureau of Statistics (ABS) revises cause-of-death data using information pertaining to coroners’ cases that was not available at the time of original processing
  • newly discovered errors or anomalies.

The latest version of a data set has been used wherever possible. In cases where the data change frequently, the date of the release is noted. Revisions and changes in coverage should be considered when interpreting changes over time.

Note: Cause of Death Unit Record File data are provided to the AIHW by the Registries of Births, Deaths and Marriages and the National Coronial Information System (managed by the Victorian Department of Justice) and include cause of death coded by the ABS. The data are maintained by the AIHW in the National Mortality Database.

Rounding

Percentages in the report are generally rounded to whole numbers except for those less than 10% which are rounded to 1 decimal place. Exceptions include the AIHW National Drug Strategy Household Survey (NDSHS) where proportions less than 20% are rounded to 1 decimal place in line with NDSHS reporting practice.

Numbers between 1,000 and 100,000 are rounded to the nearest hundred. Numbers over 100,000 are rounded to the nearest 1,000.

As a result of rounding, entries in columns and rows of tables as well as figures may not add to the totals shown. Unless otherwise stated, derived values are calculated using unrounded numbers.

Population data

The ABS estimated resident population (ERP) data were used to calculate most of the rates presented in this report for administrative data collections. Exceptions are where the denominator was available from within the data source.

Age-specific rates were calculated using the ERP of the reference year as at 30 June for calendar year data (1 January to 30 December) and 31 December for financial year data (1 July to 30 June). The denominator for rates by socioeconomic disadvantage and remoteness area were calculated by applying an ABS concordance between statistical areas (SA2) and socioeconomic disadvantage and between statistical areas and remoteness area, to the relevant ERP by SA2 counts.

Use of italics

Italics are used in this report:

  • for remoteness categories derived using the Australian Statistical Geography Standard. The main categories are Major cities, Inner regional, Outer regional, Remote and Very remote 
  • for publication titles.