National Indigenous Reform Agreement: PI 05-Prevalence of overweight and obesity, 2020; Quality Statement
Data Quality Statement Attributes
Identifying and definitional attributes
|Metadata item type:||Data Quality Statement|
Indigenous, Standard 06/02/2020
The National Aboriginal and Torres Strait Islander Health Survey (NATSIHS) and National Health Survey (NHS) were collected, processed, and published by the Australian Bureau of Statistics (ABS). The ABS operates within a framework of the Census and Statistics Act 1905 and the Australian Bureau of Statistics Act 1975. These ensure the independence and impartiality from political influence of the ABS, and the confidentiality of respondents.
For more information on the institutional environment of the ABS, including the legislative obligations of the ABS, financing and governance arrangements, and mechanisms for scrutiny of ABS operations, see ABS Institutional Environment.
The NATSIHS is conducted approximately every six years. The 2018-19 NATSIHS was conducted between July 2018 and April 2019. Previous NATSIHS was collected in 2012-13 and 2004-05. Results from the 2018-19 NATSIHS were released in December 2019.
The NHS is conducted approximately every three years. The 2017-18 NHS was conducted from July 2017 to June 2018. Previous surveys were conducted in 1989-90, 1995, 2001, 2004-05, 2007-08, 2011-12 and 2014-15. Results for the 2017-18 NHS were released in December 2018.
See National Aboriginal and Torres Strait Islander Health Survey, 2018–19 (ABS 2019) and National Health Survey: First Results 2017–18 (ABS 2018) for an overview of results.
Data from these surveys are also accessible in the DataLab and TableBuilder environment. For further details, refer to the Microdata Entry Page on the ABS website.
Other information from these surveys may also be requested from the ABS.
Information to aid interpretation of the data is available from the:
available on the ABS website.
Many health-related issues are closely associated with age, therefore data for this indicator have been age-standardised to the 2001 total Australian population to account for differences in the age structures of the states and territories and Indigenous and non-Indigenous populations. Age- standardised rates should be used to assess the relative differences between groups, not to infer the rates that actually exist in the population.
The 2018-19 NATSIHS and 2017-18 NHS collected measured height and weight from persons aged 2 years and over who agreed for the measurements to be taken. For the purposes of this indicator, Body Mass Index (BMI) values are derived using Quetelet's metric body mass index which is calculated as: weight (kg) / height (m)2.
Despite some limitations, BMI is widely used internationally as a relatively straightforward way of measuring overweight and obesity.
The NATSIHS was conducted in all states and territories, including very remote areas. Non-private dwellings such as hotels, motels, hospitals, nursing homes and short-stay caravan parks were excluded from the survey. The final response rate for the 2018-19 NATSIHS was 73.4%. Results are weighted to account for non-response.
The NHS was conducted in all states and territories, excluding very remote areas. Non-private dwellings such as hotels, motels, hospitals, nursing homes and short-stay caravan parks were also not included in the survey. The exclusion of persons usually residing in very remote areas has only a minor effect on estimates for individual states and territories, except for the Northern Territory where such persons make up approximately 20% of the population. The response rate for the 2017–18 NHS was 76.1%. Results are weighted to account for non-response.
In the 2018-19 NATSIHS and 2017-18 NHS, voluntary measurements of height and weight were collected from respondents. Physical measurement variables have a relatively high rate of non-response, compared to other variables, due to respondent sensitivities and the voluntary nature of these questions. For respondents with missing height and weight values, their record received a donor record response from a similar respondent.
As data are drawn from a sample survey, data for the indicator are subject to sampling error. Sampling error occurs because only a small proportion of the population is used to produce estimates that represent the whole population. Sampling error can be reliably estimated as it is calculated based on the scientific methods used to design surveys.
Estimates should be considered with reference to their corresponding relative standard error (RSE) of estimate Estimates with an RSE of estimate between 25% and 50% should be used with caution. Estimates with an RSE of estimate over 50% are considered too unreliable for general use.
Proportions should be considered with reference to their corresponding 95% margin of error (MOE) of proportion (or 95% confidence interval). The proportion combined with the MOE of proportion defines a range which is expected to include the true population value with a given level of confidence. This is known as the confidence interval. Proportions with an MOE of proportion greater than 10 percentage points indicate that the range in which the true population value is expected is relatively wide and are subject to high sample variability. Particular consideration should be given to the MOE of proportion when using them. Depending on how the proportion is to be used, an MOE of proportion greater than 10 percentage points may be considered too large to inform decisions. In addition, proportions with a corresponding standard 95% confidence interval that includes 0% or 100% are usually considered unreliable for most purposes.
The methods used to construct the indicator are consistent and comparable with other collections and with international practice.
The age- and sex-specific cut off points for BMI categories for children are from the work of Cole, Bellizzi, Flegal and Dietz (2000).
Most surveys, including Computer Assisted Telephone Interviewing (CATI) health surveys conducted by the states and territories, collect only self-reported height and weight. There is a general tendency across the population for people to overestimate height and underestimate weight, which results in BMI scores based on self-reported height and weight to be lower than BMI scores based on measured height and weight.
The 2004–05 NATSIHS and NHS collected self-reported data only and are therefore not comparable with 2011–13 and 2017-19 data, which are based on measured height and weight.
The 2017–19 NATSIHS and NHS used imputation for missing values for measured height and weight. For comparisons to earlier years, the ABS recommends using proportion comparisons only as imputation was not used on the physical measurement data prior to the 2018-19 NATSIHS and 2014-15 NHS.
The NATSIHS and NHS collected a range of other health-related information that can be analysed in conjunction with BMI.
Source and reference attributes
Australian Bureau of Statistics
ABS (Australian Bureau of Statistics) 2018a. National Health Survey: First Results, 2017–18. ABS Cat. no. 4364.0.55.001. Canberra: ABS.
ABS 2018b. National Health Survey: Users' Guide, 2017-18. ABS Cat. no. 4363.0. Canberra: ABS.
ABS 2019. National Aboriginal and Torres Strait Islander Health Survey, 2018–19. ABS Cat. no. 4715.0. Canberra: ABS.
Cole TJ, Bellizzi MC, Flegal KM & Dietz WH 2000. Establishing a standard definition for child overweight and obesity worldwide: international survey, BMJ 320:1240.
|Related metadata references:|
Supersedes National Indigenous Reform Agreement: PI 05-Prevalence of overweight and obesity, 2019; Quality Statement
Indigenous, Standard 07/02/2019
|Indicators linked to this Data Quality statement:|