Abstract
Official population estimates in Australia are derived from the five-yearly population census supplemented by undercount rates, which estimate the number of people missed in the census. Between censuses, population growth is modelled using component- and regression-based methods. After each census, these modelled estimates are superseded by the new census-based, or rebased, estimates. However, major differences between the 2011 modelled and census-based estimates, caused by a change in the way the census undercount rate was derived, led to a one-off ‘recasting’ revision to 20 years of historical population estimates. This extraordinary revision process led to a revisit of the approach to rebasing adopted in response to past censuses, where it was found that strict reliance on volatile census undercount rates, regardless of methodological changes, led to implausible population change between censuses. Discounting the modelled estimates or any other data source that indicates population change between censuses had a detrimental impact on the quality of the rebased estimates before recasting. Lessons learned from the recasting exercise could be used to improve the quality of Australia’s population estimates from the 2016 census and beyond.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
There are six states, two major territories (Northern Territory and Australian Capital Territory) and three external territories for which these quarterly estimates are prepared. The three external territories are referred to in aggregate as ‘Other Territories’. The following abbreviations are used: NSW – New South Wales (state); Vic – Victoria (state); Qld – Queensland (state); SA – South Australia (state); WA – Western Australia (state); Tas – Tasmania (state); NT – Northern Territory; ACT – Australian Capital Territory; OT – Other Territories.
- 2.
At the sub-state level, population estimates are prepared for many different geographies. The main sub-state geographies are Statistical Areas Level 2 (SA2s) and Local Government Areas (LGAs). SA2s are medium-sized general purpose areas which aim to represent communities that interact together socially and economically, and are the lowest level of Australia’s statistical geography for which ERP is made generally available. SA2s form or combine to form SA3s (which reflect widely recognised informal and administrative regions), SA4s (designed to reflect labour markets in urban areas, and aggregations of remaining areas) and Greater Capital City Statistical Areas or GCCSAs (which represent a broad socioeconomic definition of the capital city of each of the eight state and major territories), sometimes referred to as capital cities. ‘Rest of state’ areas are defined as those remaining areas of each state and the Northern Territory; the Australian Capital Territory consists wholly of the capital city GCCSA. LGAs are officially gazetted incorporated areas of Australia, which are legally designated regions for which incorporated local governing bodies have responsibility. In 2011 there were 2160 populated SA2s, 333 populated SA3s, 88 populated SA4s and 558 Local Government Areas.
- 3.
As the undercount rates are derived from a sample survey, the Post Enumeration Survey (PES), standard errors for estimates derived from the PES are also available (ABS 2012b). For Australia’s 2011 net undercount rate of 374,500 people (or 1.7 %) for example, the standard error was 38,300. Under standard statistical survey treatment, there was 95 % confidence that the true 2011 Census net undercount rate was between 297,900 and 451,200, or 374,500 plus/minus two times the standard error. For rest of Victoria, the 95 per cent confidence bound ranged from −17,800 (ie. a net overcount) and 21,400.
- 4.
Adjustments to estimated resident population, by part of state
Adjustment to ERP 1996
Adjustment to ERP 2001
Adjustment to ERP 2006
Part of state
Number
Percent
Number
Percent
Number
Percent
NSW capital city
−24,484
−0.63
−25,767
−0.62
−25,900
−0.60
Rest of NSW
−3783
−0.16
−19,101
−0.78
−47,497
−1.87
VIC capital city
−23,800
−0.71
−21,690
−0.62
−38,228
−1.01
Rest of VIC
−1371
−0.11
−19,421
−1.51
−27,046
−2.04
QLD capital city
−20,786
−1.31
−20,764
−1.21
−6611
−0.35
Rest of QLD
−14,712
−0.84
−36,713
−1.92
−76,305
−3.51
SA capital city
−4527
−0.40
−6736
−0.58
−10,362
−0.86
Rest of SA
−647
−0.18
−1531
−0.43
−4997
−1.36
WA capital city
−1023
−0.08
3303
0.23
−13,095
−0.82
Rest of WA
3973
0.94
1812
0.40
4295
0.92
TAS capital city
405
0.21
−893
−0.45
−1840
−0.89
Rest of TAS
757
0.27
2766
1.01
1191
0.42
NT capital city
1418
1.48
1438
1.35
−901
−0.79
Rest of NT
1255
1.46
2537
2.79
−669
−0.69
ACT
1378
0.45
2221
0.70
1051
0.31
- 5.
Changes to population growth, by part of state
Population growth 2006–11, number
Population growth 2006–11, percent
Part of state
Before recasting
After recasting
Change, number
Change, percent
Before recasting
After recasting
Change
NSW capital city
323,931
352,788
28,857
8.9
7.6
8.3
0.7
Rest of NSW
71,450
123,051
51,601
72.2
2.8
4.9
2.1
VIC capital city
370,115
408,606
38,491
10.4
9.7
10.9
1.1
Rest of VIC
37,871
67,945
30,074
79.4
2.9
5.2
2.4
QLD capital city
231,701
239,171
7470
3.2
12.1
12.5
0.4
Rest of QLD
151,489
229,615
78,126
51.6
7.0
10.9
4.0
SA capital city
63,335
74,848
11,513
18.2
5.3
6.3
1.0
Rest of SA
7009
12,237
5228
74.6
1.9
3.4
1.5
WA capital city
242,107
256,655
14,548
6.0
15.2
16.3
1.0
Rest of WA
50,727
46,173
−4554
−9.0
10.8
9.7
−1.1
TAS capital city
9683
11,520
1837
19.0
4.7
5.6
0.9
Rest of TAS
11,561
10,661
−900
−7.8
4.1
3.7
−0.3
NT capital city
14,700
15,645
945
6.4
12.9
13.8
0.9
Rest of NT
6004
6590
586
9.8
6.2
6.9
0.7
ACT
33,633
32,815
−818
−2.4
10.1
9.8
−0.3
- 6.
Net undercount rates, by part of state, 1991–2011 censuses
Area
1991 percent
1996 percent
2001 percent
2006 percent
2011 percent
NSW capital city
2.0 (0.2)
1.8 (0.2)
1.5 (0.2)
3.0 (0.5)
1.8 (0.5)
Rest of NSW
1.7 (0.2)
1.1 (0.4)
2.8 (0.4)
1.3 (0.6)
2.2 (0.7)
VIC capital city
1.7 (0.2)
1.7 (0.3)
1.0 (0.2)
2.4 (0.5)
1.4 (0.4)
Rest of VIC
2.0 (0.3)
1.5 (0.5)
2.5 (0.4)
2.0 (0.7)
0.1 (0.7)
QLD capital city
1.4 (0.1)
1.4 (0.3)
1.0 (0.2)
1.9 (0.8)
2.0 (0.5)
Rest of QLD
2.6 (0.2)
2.1 (0.5)
2.7 (0.4)
5.1 (0.8)
1.5 (0.6)
SA capital city
1.2 (0.1)
0.7 (0.3)
1.5 (0.2)
2.2 (0.5)
1.1 (0.4)
Rest of SA
2.2 (0.4)
2.3 (0.9)
1.9 (0.5)
2.8 (0.8)
0.9 (0.8)
WA capital city
1.4 (0.2)
1.2 (0.2)
1.6 (0.3)
2.7 (0.7)
2.9 (0.6)
Rest of WA
4.1 (0.5)
2.5 (1.3)
3.1 (0.7)
4.4 (1.3)
1.2 (1.3)
TAS capital city
1.6 (0.2)
1.5 (0.9)
1.5 (0.4)
1.3 (1.1)
0.6 (1.0)
Rest of TAS
1.9 (0.2)
1.4 (0.5)
1.6 (0.7)
2.5 (0.0)
3.1 (1.0)
NT capital city
n.a.
n.a.
n.a.
5.5 (1.7)
3.7 (1.7)
Rest of NT
n.a.
n.a.
n.a.
10.1 (2.4)
10.9 (1.9)
ACT
1.8 (0.3)
1.6 (0.3)
1.0 (0.4)
1.2 (1.0)
0.7 (0.8)
Total capital city
1.7 (0.1)
1.5 (0.1)
1.3 (0.1)
2.5 (0.3)
1.8 (0.2)
Total rest of state
2.2 (0.1)
1.7 (0.1)
2.6 (0.2)
3.0 (0.4)
1.7 (0.3)
Australia
1.8 (0.1)
1.6 (0.1)
1.8 (0.1)
2.7 (0.2)
1.7 (0.3)
- 7.
Change in net undercount, by part of state, 1991–2011 censuses
Area
1991–1996 number (‘000)
1996–2001 number (‘000)
2001–2006 number (‘000)
2006–2011 number (‘000)
NSW capital city
−2.6
−6.4
63.2
−45.1
Rest of NSW
−12.1
42.9
−35.7
24.2
VIC capital city
3.3
−18.8
52.6
−31.6
Rest of VIC
−5.9
14.3
−6.2
−25.1
QLD capital city
2.9
−5.5
18.7
7.6
Rest of QLD
−1.8
12.6
61.2
−78.8
SA capital city
−4.5
8.9
8.0
−10.4
Rest of SA
0.8
−1.3
4.0
−8.6
WA capital city
−0.9
6.3
18.8
11.0
Rest of WA
−5.9
3.4
7.9
−17.2
TAS capital city
−0.1
0.2
−0.4
−1.2
Rest of TAS
−1.3
0.6
2.6
2.0
NT capital city
n.a.
n.a.
n.a.
−1.6
Rest of NT
n.a.
n.a.
n.a.
1.4
ACT
0.8
−0.6
0.7
−1.4
Total capital city
−1.9
−12.1
167.9
−72.7
Total rest of state
−26.3
72.5
43.3
−102.2
Australia
−28.3
57.7
203.4
−174.9
- 8.
Intercensal difference, by part of state, 1996–2011
Area
1996 number (‘000)
2001 number (‘000)
2006 number (‘000)
2011 number (‘000)
NSW capital city
25.7
−59.7
12.5
11.1
Rest of NSW
−23.0
45.1
−55.2
0.5
VIC capital city
−3.4
−34.6
50.5
−58.6
Rest of VIC
10.2
15.5
−26.2
23.7
QLD capital city
11.1
6.4
5.2
−0.2
Rest of QLD
−0.9
9.3
−6.3
−37.2
SA capital city
8.0
7.4
−8.1
−7.4
Rest of SA
1.6
−2.8
−0.8
−5.9
WA capital city
21.7
−12.3
7.5
−10.8
Rest of WA
8.2
9.8
1.1
2.3
TAS capital city
−2.4
−0.8
−2.7
0.0
Rest of TAS
−3.8
−0.2
1.2
−1.0
NT capital city
−2.1
−1.5
0.8
−0.3
Rest of NT
−1.8
−1.6
1.6
−3.6
ACT
4.2
−1.2
−4.3
−5.4
Total capital city
58.6
−95.2
65.8
−66.2
Total rest of state
−9.6
75.0
−84.7
−21.2
Australia
49.1
−20.2
−18.9
−87.4
- 9.
Analysis of intercensal difference at the LGA level prior to 2001–2006 based on the recast series was not able to be made at the LGA level as regression-based LGA-level estimates prior to 2001–2006 were not prepared on the same boundaries as the recast series. Regression-based population estimates prior to 2011 were not prepared due to the SA2 geography not being established until 2011.
References
ABS. (1998). Issues in estimating small area populations, Australian Bureau of Statistics Working Paper 98/1.
ABS. (2004). Assessing the accuracy of Australia’s small area population estimates, 2001. Paper presented at the Australian Population Association conference, Canberra, 2004.
ABS. (2007a). Census of population and housing details of undercount, August 2006, cat. no. 2940.0.
ABS. (2007b). An estimating equation approach to census coverage adjustment, cat. no. 1351.0.55.019.
ABS. (2008). Assessing the accuracy of Australia’s regional population estimates, 2006. Paper presented at the Australian Population Association conference, Alice Springs, 2008.
ABS. (2009). Population estimates: Concepts, sources and methods, 2009, cat. no. 3228.0.55.001.
ABS. (2011). Australian Bureau of Statistics 2011, Australian demographic statistics, June 2011, cat. no. 3101.0.
ABS. (2012a). Australian Bureau of Statistics 2012(a), Regional population growth, Australia, 2010–11, cat. no. 3218.0.
ABS. (2012b). Australian Bureau of Statistics 2012(b), census of population and housing, details of undercount, 2011, cat. no. 2940.0.
ABS. (2012c). Australian Bureau of Statistics 2012(c), Australian demographic statistics, December 2011, cat. no. 3101.0.
ABS. (2012d). Australian Bureau of Statistics 2012(d), Regional population growth, Australia, 2011, cat. no. 3218.0.
ABS. (2012e). Australian Bureau of Statistics 2012(e), Australian demographic statistics, March 2012, cat. no. 3101.0.
ABS. (2012f). Australian Bureau of Statistics 2012(f), Australian demographic statistics, June 2012, cat. no. 3101.0.
ABS. (2013a). Australian Bureau of Statistics 2013(a), Regional population growth, Australia, 2011–12, cat. no. 3218.0.
ABS. (2013b). Australian Bureau of Statistics 2013(b), Australian demographic statistics, December 2012, cat. no. 3101.0.
ABS. (2013c). Australian Bureau of Statistics 2013(c), Regional population growth, Australia, 2012, cat. no. 3218.0.
ABS. (2015). Australian Bureau of Statistics 2015, Migration, Australia, 2013–14, cat. no. 3412.0.
Acknowledgements
With thanks to Phil Browning, Tricia Chester, Beidar Cho, AJ Lanyon and Michael Roden for their useful comments in the production of this chapter.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Howe, A. (2017). Revising Long-Established Population Estimates in Australia: Reasons, Methods and Implications. In: Swanson, D. (eds) The Frontiers of Applied Demography. Applied Demography Series, vol 9. Springer, Cham. https://doi.org/10.1007/978-3-319-43329-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-43329-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-43327-1
Online ISBN: 978-3-319-43329-5
eBook Packages: Social SciencesSocial Sciences (R0)