SAMPLING


SCOPE AND COVERAGE

Scope

The Survey of Income and Housing (SIH) and Household Expenditure Survey (HES) collects information by personal interview from usual residents of private dwellings in urban and rural areas of Australia (excluding Very Remote areas), covering about 97% of the people living in Australia. Private dwellings are houses, flats, home units, caravans, garages, tents and other structures that were used as places of residence at the time of interview. Long-stay caravan parks are also included. These are distinct from non-private dwellings which include hotels, boarding schools, boarding houses and institutions. Residents of non-private dwellings are excluded. Usual residents excludes:

• households that contain members of non-Australian defence forces stationed in Australia;
• households that contain diplomatic personnel of overseas governments; and
• households in areas defined as Very Remote - this has only a minor impact on aggregate estimates, except in the Northern Territory where such households account for about 22% of the population.

For most states and territories, the exclusion of people in Very Remote areas has only a minor impact on any aggregate estimates that are produced because they constitute just a small proportion of the population. Very Remote and Remote areas are defined by the assignment of an Accessibility/Remoteness Index of Australia (ARIA) score. ARIA is a remoteness value (a continuous variable between 0 and 15) that measures the physical distance which separates people in a particular area and where their goods, services and opportunities for social interaction may be accessed.

The ARIA categories, and how ARIA scores are calculated, are further explained in the Australian Statistical Geography Standard (ASGS): Volume 5 - Remoteness Structure, July 2011 (cat. no. 1270.0.55.005).

Coverage

Information was collected only from usual residents. Usual residents were residents who regarded the dwelling as their own or main home. Other people present were considered to be visitors and were not asked to participate in the survey.


SAMPLE DESIGN AND SELECTION

Sample design

The SIH and HES sample were designed to produce reliable estimates for broad aggregates of income, wealth, housing and expenditure data for household residents in private dwellings of Australia, the State and Territories and for the capital cities and rest of state. More detailed estimates should be used with caution, especially for Tasmania, the Northern Territory and the Australian Capital Territory due to smaller samples in these localities. For more information see the 'Reliability of Estimates' section of this publication.

The SIH and HES samples were designed together. HES is a subsample of the SIH sample and some dwellings were selected to complete both the SIH and HES questions while others were selected to complete only the SIH questions. In 2015-16 dwellings were selected through a stratified, multistage cluster design from the private dwelling framework of the ABS Population Survey Master Sample. Selections were distributed across a twelve month enumeration period so that the survey results are representative of income and expenditure patterns across the year.

For the 2015-16 SIH and HES there was an additional sample of capital city households, targeting households whose main source of income was government pensions, benefits and/or allowances. These households were enumerated using a separate sample design, and received the combined SIH and HES questionnaires. In this additional sample, dwellings were targeted using information from the previous HES (2009-10), and information from the Socio-Economic Indexes for Areas (SEIFA). Households were screened using a short questionnaire to identify whether pensions and benefits were likely to be the main source of income for the household. 23,870 households were screened. One in four households were selected to complete the combined SIH and HES questionnaire and diaries regardless of the screening outcome. Information from this sample were used to assess the outcomes from the screening questionnaire for the whole sub-sample.

SIH selected dwellings, sample loss and selected households

In the 2015-16 SIH, 29,815 dwellings were initially selected for the main sample. When fieldwork commenced some dwellings selected for inclusion in the main sample were found to be out of scope units. Collectively these are referred to as sample loss, and are composed of the following groups:

• dwellings that are out of scope of the survey, under construction, demolished, or converted to non-private dwellings or non-dwellings;
• vacant private dwellings; and
• private dwellings that contain only visitors or out of scope residents (e.g. dwellings occupied by foreign diplomats and their dependants).

In 2015–16, the SIH sample loss was 4,883 dwellings which accounted for 16% of the selected sample.

Sometimes dwellings that have been selected for inclusion in a survey are found to comprise more than one actual dwelling because an additional residence, such as a 'granny flat', has been added to the original dwelling. In such cases, each actual dwelling becomes a separate household. For privacy reasons, residents of a selected dwelling can request that their details be provided separately from other dwelling residents. A separate household is then created for each group of residents. In 2015-16 SIH , 56 selected dwellings were split into two households and 21 were split into three or more households.

A further 7,164 (24%) did not respond at all to the questionnaire, or did not respond adequately. Most of these were not able to take part in the survey during the collection period or were contacted but either refused to respond or were not able to respond adequately. The remainder of these households included:

• households affected by death or illness of a household member;
• households which did not respond because due to communication barriers or because they refused to participate (7.6% of all contacted households).

126 households were excluded because the main income earners in the household did not adequately respond to questions about income sources and amounts. 229 households that were collected as part of the HES sample but did not have sufficient expenditure diary information were retained as part of the SIH sample.

Final SIH sample

Of the selected dwellings (24,932) that were contacted and in scope of the survey, 17,768 (71%) households were included as part of the final estimates.

SIH FINAL SAMPLE, 2015–16
	GREATER CAPITAL CITY		REST OF STATE		TOTAL
	Households	Persons (a)	Households	Persons (a)	Households	Persons (a)
	no.	no.	no.	no.	no.	no.
NSW	2 212	4 357	910	1 718	3 122	6 075
Vic.	2 526	5 023	1 119	2 053	3 645	7 076
Qld	1 505	2 924	1 153	2 189	2 658	5 113
SA	1 675	3 167	1 105	1 990	2 780	5 157
WA	1 427	2 825	1 088	2 027	2 515	4 852
Tas.	709	1 279	1 104	1 976	1 813	3 255
NT	418	805	83	146	501	951
ACT	734	1 489	-	-	734	1 489
Aust.	11 206	21 869	6 562	12 099	17 768	33 968
- nil or rounded to zero (including null cells) (a) Number of persons aged 15 years and over

The SIH sample is not evenly balanced over the course of the year. Due to under-performance of the sample design in the first half of the collection year, a top-up sample was selected and collected from January - July 2016. The fully responding households by each half of the collection year are provided in the table below.

Weights adjust by quarter to ensure representativeness across the year.

	July-December 2015	January-July 2016	Full Collection Period	July-December 2015	January-July 2016	Full Collection Period
	no.	no.	no.	%	%	%
NSW	1 276	1 846	3 122	40.9	59.1	100
Vic.	1 622	2 023	3 645	44.5	55.5	100
Qld	1 105	1 553	2 658	41.6	58.4	100
SA	1 246	1 534	2 780	44.8	55.2	100
WA	966	1 549	2 515	38.4	61.6	100
Tas.	858	955	1 813	47.3	52.7	100
NT	227	274	501	45.3	54.7	100
ACT	316	418	734	43.1	56.9	100
Aust.	7 616	10 152	17 768	42.9	57.1	100

HES selected dwellings, sample loss and selected households

Of the selected dwellings for HES there were 17,873 households in the scope of the survey. Of this initial sample, 2,579 dwellings (14%) were excluded as no contact was able to be made (e.g, vacant dwelling, holiday homes). A further 5,220 (29%) did not respond at all to the questionnaire, or did not respond adequately. Most of these were not able to take part in the survey during the collection period or were contacted but either refused to respond or were not able to respond adequately. The remainder of these households included:

• households affected by death or illness of a household member; and
• households which did not respond because due to communication barriers or because they refused to participate (9.5% of all contacted households).

110 households were excluded because the main income earners in the household did not adequately respond to questions about income sources and amounts. 229 households that were collected as part of the HES sample but did not have sufficient expenditure diary information were retained as part of the SIH sample. 74 households were retained after repair to an instrument error.

In 2015-16 HES, 34 selected dwellings were split into two households and 12 were split into three or more households.

Final HES sample

Of the selected dwellings (15,294) that were contacted and in scope of the survey, 10,046 (66%) households were included as part of the final estimates.

HES FINAL SAMPLE, 2015–16
	GREATER CAPITAL CITY		REST OF STATE		TOTAL
	Households	Persons (a)	Households	Persons (a)	Households	Persons (a)
	no.	no.	no.	no.	no.	no.
NSW	1 778	4 344	479	1 151	2 257	5 495
Vic.	2 004	4 761	386	866	2 390	5 627
Qld	1 050	2 491	439	1040	1 489	3 531
SA	1 044	2 332	254	537	1 297	2 869
WA	1 002	2 365	216	543	1 215	2 908
Tas.	557	1 242	204	428	763	1 670
NT	259	603	81	189	337	792
ACT	293	734	-	-	295	734
Aust.	7 987	18 872	2 059	4 754	10 046	23 626
- nil or rounded to zero (including null cells) (a) Number of persons aged 15 years and over

The HES sample is not evenly balanced over the course of the year. Due to under-performance of the sample design in the first half of the collection year, a top-up sample was selected and collected from January - July 2016. The fully responding households by each half of the collection year are provided in the table below.

Weights adjust by quarter to ensure representativeness across the year.

	July-December 2015	January-July 2016	Full Collection Period	July-December 2015	January-July 2016	Full Collection Period
	no.	no.	no.	%	%	%
NSW	893	1 364	2 257	39.6	60.4	100.0
Vic.	980	1 410	2 390	41.0	59.0	100.0
Qld	567	922	1 489	38.1	61.9	100.0
SA	548	750	1 298	42.2	57.8	100.0
WA	470	748	1 218	38.6	61.4	100.0
Tas.	333	428	761	43.8	56.2	100.0
NT	154	186	340	45.3	54.7	100.0
ACT	119	174	293	40.6	59.4	100.0
Aust.	4 064	5 982	10 046	40.5	59.5	100.0

Additional pensioner sample

The collection methodology for the pensioner sample was a two phase approach. In the first phase, a large number of households were required to answer a number of short screening questions to identify whether they were a pensioner household. In the second phase, one in four of the in scope selected households were selected for inclusion in HES survey regardless of the screening outcome. In addition, households which were screened as pensioner households were selected for interview using the same collection methodology as for the HES. The screening questions are included in the downloads tab of this publication. For the 2015-16 additional pensioner sample, 23,870 dwellings were screened. After the screening process 5,845 households were approached to complete the SIH and HES surveys. There were 3,603 households from this approached sample that responded with sufficient information to be included within the final SIH and HES samples.