SAMPLE DESIGN AND SELECTION

Sample design

The 2011-12 NHS and NNPAS were conducted using a stratified multistage area sample of private dwellings. The sample size, distribution and method of selection was based on the aims of the survey, the topics they contained, the level of disaggregation and accuracy at which the survey estimates were required, and the costs and operational constraints of conducting the survey. The sample was designed to provide:

• relatively detailed estimates for each state/territory and Australia
• relatively detailed estimates for Capital City/Balance of State areas within each state and territory
• broad level estimates for regions within larger states and territories
• estimates for those characteristics which are relatively common, and sub-populations which are relatively large and spread fairly evenly geographically.

To achieve these design objectives, state and territory sampling fractions were set as shown in the following table, which also depicts the corresponding expected number of fully responding households. The sample selection procedures described below result in every dwelling in the same state or territory having a known probability of selection, equal to the state or territory sample fraction.

	NSW	Vic.	Qld	SA	WA	Tas.	NT	ACT	Aust.
Approximate sampling fractions	1/1004	1/854	1/702	1/340	1/414	1/142	1/62	1/106	1/551
Expected fully responding households	2 800	2 640	2 530	2 000	2 100	1 470	1 150	1 310	16 000

	NSW	Vic.	Qld	SA	WA	Tas.	NT	ACT	Aust.
Approximate sampling fractions	1/1649	1/1568	1/1131	1/551	1/665	1/208	1/102	1/169	1/901
Expected fully responding households	1 750	1 650	1 580	1 250	1 310	920	740	820	10 020

Actual numbers of fully responding households are available in the Response rates section of this chapter.

Within selected dwellings, a random sub-sample of residents was selected as follows:

• one adult (aged 18 years and older), and (where applicable)
• one child aged 0-17 years (NHS)
• one child aged 2-17 years (NNPAS).

For NNPAS, the random sample selection code in the survey instrument was designed to give adults aged 65 years and over a double chance of being selected in the sample in order to improve estimates for this older age group.

All selected persons aged 5 years and over were also invited to participate in the voluntary Biomedical component of the surveys.

Sample selection

The area-based selection ensures that all sections of the population living in private dwellings within the geographic scope of the survey (i.e. excludes very remote and Indigenous Communities) were represented by the sample. Each state and territory was divided into geographically homogenous (usually contiguous) areas called strata. Strata are formed by initially dividing Australia into regions, which are formed within state/territory boundaries, and which basically correspond to the Statistical Division or Statistical Subdivision levels of the Australian Standard Geographical Classification (ASGC) (cat. no.1216.0). Each stratum contains a number of Census Collection Districts (CDs). A CD on average contains around 250 dwellings.

In capital cities and other major urban or high population density areas, the dwelling sample was selected in three stages:

• CDs, i.e. a systematic sample of CDs was selected from each stratum with probability proportional to the number of dwellings in each CD
• blocks, i.e. each selected CD was divided into groups of dwellings or blocks of similar size, and one block was selected from each CD, with probability proportional to the number of dwellings in the block
• dwellings, i.e. each selected block a list of all private dwellings was prepared and a systematic random sample of dwellings was selected.

In strata classified as high population growth the CD stage of selection was omitted, leaving only two stages of selection, i.e. the strata was divided into blocks and then dwellings were selected within each group.

In strata with low population density each stratum was initially divided into units, usually corresponding to towns or Statistical Local Areas (SLAs), or combinations of both, and one or two units were selected from each stratum. Within selected units, the sample of dwellings was arrived at in the same manner as outlined for high population density areas, with one exception. Where CDs contained both urban and rural components, with one component comprising at least 30% of the dwellings, these were split and a block selected within each.

In the NHS a total sample of approximately 21,100 households was selected which, taking account of an expected rate of sample loss (e.g. vacant dwellings, dwellings under construction, etc.) of 14% and an expected rate of non-response of 10%, was designed to achieve the desired sample of around 16,000 fully responding households.

In the NNPAS a total sample selection of approximately 14,200 households which, taking into account an expected rate of sample loss of 14% and an expected rate of non-response of 15%, was designed to achieve the desired sample of around 10,000 fully responding households.

To take account of possible seasonal effects on health characteristics (including nutrition and physical activity) and biomedical test results (including Vitamin D), the NHS and NNPAS were enumerated over 12-month periods. NHS was enumerated from 6 March 2011 to 17 March 2012. NNPAS was enumerated from 29 May 2011 to 9 June 2012. Collection Districts were allocated randomly over five sub-periods:

• March 2011 to May 2011 (NHS only)
• June 2011 to August 2011
• September 2011 to November 2011
• December 2011 to March 2012
• April 2012 to June 2012 (NNPAS only).

A pause in enumeration occurred between 6 August 2011 and 2 October 2011, to facilitate field work associated with the 2011 Census of Population and Housing.

The collection of the NHMS (i.e. the Biomedical component of the NHS and NNPAS) commenced in March 2011 and finished in September 2012.

Previous Page

Next Page