Statistical methodology
Suicide incidence rates
This report uses incidence rates to measure how often suicide occurs among the 3 ADF service groups, as well as in the Australian population. The incidence rate is the total number of deaths by suicide in a population over a specific period, divided by population time at risk during this period. In this study, the sum of the population at 30 June in each year of the relevant period is used as a proxy for population time at risk. Suicide incidence rates are expressed as the number of deaths per 100,000 population per year. While the measure of suicide rate in this report is standardised to 100,000 population per year, it is important to recognise that the population per year for some groups may be less than 100,000.
Rates based on small numbers
Rates based on small numbers of events can fluctuate from year to year for reasons other than a true change in the underlying risk of the event.
In this report, rates are not reported when there are fewer than 5 events, as rates produced using small numbers can be sensitive to small changes in counts of deaths over time. Numbers smaller than 5 have also been suppressed to minimise disclosure risks.
In this report, rates denoted with an asterisk (*) should be interpreted with caution as the number of events is fewer than 20. These rates are subject to large fluctuations.
Standardised mortality ratios
Age-adjusted comparisons between the suicide rate in each of the 3 ADF service status groups and the Australian population were calculated using Standardised Mortality Ratios (SMRs). The SMR is a widely recognised measure used to account for differences in age structures when comparing death rates between populations. This method of standardisation can be used when analysing relatively rare events, that is, where the number of deaths is less than 25 within a period. The SMR is used to control for the fact that the ADF service status groups have a different age profile than the Australian population, and rates of suicide vary by age in both the ADF populations and the Australian population. The SMRs control for these differences, enabling comparisons of suicide counts between the service status groups and general Australian population without the confounding effect of differences in age.
The SMR is calculated as the observed number of events (deaths by suicide) in the study population divided by the number of events that would be expected if the study population had the same age- and sex-specific rates as the comparison population. SMRs greater than 1.0 indicate a greater number of suicides in the ADF population than expected relative to the general Australian population; and SMRs less than 1.0 indicate a lower number of suicides in the ADF population than expected relative to the general Australian population.
Unlike suicide rates, SMRs only provide information about the 2 populations upon which the statistic is based. Comparing SMRs cannot be used to draw conclusions about the relative adjusted mortality rates of the study populations. This is because each SMR measure provides a comparison that is specific to the 2 populations involved.
Comparisons with the general Australian population are not calculated for other characteristics of the ADF population such as length of service and rank, as the adjustment for age and sex do not account for all the differences in the populations. Additionally, it is considered more useful to make comparisons within the ADF population for the different levels of these characteristics (rather than between the ADF and the general Australian population).
Confidence Intervals
This report provides 95% confidence intervals (95% CIs) for suicide rates and Standardised Mortality Ratios (SMRs). A 95% CI means that if the same study were repeated many times, 95% of the resulting confidence intervals calculated from those studies would contain the true value. Wider confidence intervals indicate greater uncertainty about the estimate, while narrower intervals suggest more precision.
It is important to note that confidence intervals are typically used to express uncertainty around estimates based on samples. However, in this report, the data represent the entire population, not a sample. As such, there is no sampling error, and confidence intervals are less relevant in this context. However, even if the number of health events is based on a complete count of an entire population, it is subject to random variation which should be considered especially when comparisons are made over time or between populations.
Using confidence intervals to test for statistical significance
A statistically significant difference means that the observed difference between two groups is unlikely to have occurred by chance alone if there is no true difference in the population. However, statistical significance does not necessarily imply that the difference is large or practically meaningful.
In this study, 95% confidence intervals (95% CIs) are provided for each suicide rate and Standardised Mortality Ratio (SMR) to indicate the level of statistical uncertainty in these estimates due to random fluctuations in the number of suicides over time. When these estimates are produced using low numbers, they can be sensitive to small changes in the absolute numbers of deaths over time and will therefore have wide CIs. The CIs in this report have been calculated based on the assumption that the suicide counts can be described by a Poisson distribution.
The use of CIs is the simplest way to test for significant differences between ADF service groups and Australian comparison groups. In this report, differences are deemed to be statistically significant if the 95% CIs do not overlap with each other (when comparing suicide rates) or do not overlap with 1.00 (in the case of an SMR). The CIs in this report cannot be used to determine the significance of differences between rates calculated for overlapping 3-year time periods.
Where the CIs are wide, for example in the case of the SMR for ex-serving females, sensitivity analyses were conducted. These analyses found that slight changes to the absolute numbers of suicides did not significantly alter the report findings.
It is important to note that there are other sources of uncertainty, such as linkage error, that are not captured by the provided CIs.
Population
The population studied in this report includes all ADF members who have served at least one day since 1 January 1985. As of 31 December 2023, around 398,000 Australians had served at least one day in the ADF between 1 January 1985 and 31 December 2023. Of these, 377,000 were alive, comprising 58,600 permanent, 39,600 reserve, and 279,000 ex-serving ADF members.
Since 1985, the ex-serving population with at least one day of service has increased each year as permanent and reserve ADF members have separated from service. At the end of 1985, there were 6,100 ex-serving members. By the end of 2023, this had increased to 297,000 ex-serving members (of whom 279,000 were alive). As members leave permanent and reserve ADF service, this report counts them as members of the ex-serving ADF population.
The permanent, reserve, and ex-serving populations have different demographics relative to the general Australian population. For example, the general Australian population is 50% male, the ADF population is 83% male. The median age for permanent, reserve, and ex-serving ADF members is 31, 37 and 53 years respectively, compared with 45 years for the Australian population over 17 years of age.
Age and sex demographic factors are considered when examining differences in suicide rates for the ADF and general Australian population.
For more information on the demographics of the ADF population, see the report: Serving and ex-serving Australian Defence Force members who have served since 1985: population characteristics 2019