2940.0 - Census of Population and Housing: Details of Overcount and Undercount, Australia, 2016 Quality Declaration 
Latest ISSUE Released at 11:30 AM (CANBERRA TIME) 27/06/2017   
   Page tools: Print Print Page Print all pages in this productPrint All RSS Feed RSS Bookmark and Share Search this Product

2016 PES SAMPLE AND RESPONSE RATES

PES SAMPLE DESIGN

1 The 2016 PES sample comprised two components: private dwellings (houses, apartments, etc.) within the General Population sample, and private dwellings within the Discrete Community sample.

2 A total of 53,800 dwellings were randomly selected in the PES sample design. Taking into account sample loss and non-response expectations, approximately 43,000 dwellings were expected to respond to the PES, including around 800 dwellings from 33 Discrete Communities in NSW, Qld, SA, WA and NT. This represented an increase of 20% on the size of the 2011 PES sample.

GENERAL POPULATION SAMPLE

3 The General Population sample was selected through a stratified, multi-stage cluster design from the private dwelling framework of the ABS Population Survey Master Sample. Areas are grouped into strata based on locality, population density, remoteness, projected population growth and socio-economic characteristics. Each private dwelling within the stratum has the same probability of selection.

4 A focused sampling strategy was introduced into the General Population sample in 2011 to improve estimates for the Aboriginal and Torres Strait Islander population. The strategy was reviewed in 2015, which showed that most of the improvement in Aboriginal and Torres Strait Islander estimates was achieved by increases to the overall sample size, rather than from the focused design. As such, the strategy was discontinued in 2016.

DISCRETE COMMUNITY SAMPLE

5 For the purposes of PES sampling, Discrete Communities were grouped into sets comprising main communities and their associated outstations. The selection of main communities was undertaken with probability proportional to the size of the set. The aim was to select as representative a sample as possible while also considering cost constraints, reasonable interviewer workloads and expected sample size.

6 The sample selection process within the Discrete Community required the interviewer to compile a list of all the dwellings within the community. From this, a sample was taken using systematic equal probability sampling.

7 A selection of outstations associated with each selected main community was also included in the sample. Each outstation had an equal chance of selection and, once selected, all dwellings within the outstation were enumerated. Occasionally, an outstation was not enumerated if it was difficult to access from the main community resulting in a small loss of coverage.

2016 RESPONSE RATES

8 The total number of fully responding dwellings across both sample components, after allowing for sample loss, was 42,463. This represented a response rate of 91.2% for the General Population sample and 92.7% for the Discrete Community sample. This is a lower than 2011, which achieved 94.0% and 96.4%, respectively.

APPROACHED SAMPLE, FINAL SAMPLE AND RESPONSE RATES

NSW
Vic.
Qld
SA
WA
Tas.
NT
ACT
Aust.

GENERAL POPULATION
Households approached (after sample loss)
10 267
8 802
8 263
4 920
5 587
2 779
3 308
1 698
45 624
Households in sample
9 147
8 034
7 634
4 587
5 211
2 638
2 791
1 555
41 597
Response rate (%)
89.1
91.3
92.4
93.2
93.3
94.9
84.4
91.6
91.2
Persons in sample
24 713
21 153
20 434
11 519
13 677
6 230
7 921
4 177
109 824
DISCRETE COMMUNITY
Households approached (after sample loss)
28
124
65
153
564
934
Households in sample
22
115
65
137
527
866
Response rate (%)
78.6
92.7
100.0
89.5
93.4
92.7
Persons in sample
52
465
313
578
2 811
4 219

Nil or rounded to zero (including null cells).