• Summary
• Downloads
• Explanatory Notes
• Related Information
• Past Releases

Estimates by marital status

2.22. Prior to 30 June 1998, annual estimates of the population by marital status were compiled quarterly and published annually as at 30 June by single years of age and sex for Australia as a whole. They commenced initially from census date estimates and were updated using the component method (ie. using data from births, deaths, marriages, divorces and migration records).

2.23. The marital status categories for which the estimates are produced (ie. single, married, widowed and divorced) refer to 'registered' marital status. People who state at the census that they are 'separated but not divorced', for example, are classified in the estimates as 'married'. People in de facto relationships are classified according to their response to Question 6 "What is the person's present marital status?" in the 1996 Census (ie. never married, widowed, divorced, separated but not divorced, married).

Census date population estimates by marital status

2.24. Population estimates by marital status, single years of age and sex are first produced for the census date, which then provides the base population from which subsequent post-censal estimates are derived. This involves the following steps:

Step 1.

2.25. Census counts of residents are compiled by single years of age and sex for each marital status category. ('Census counts of residents' necessarily means that overseas visitors who are counted in the census are excluded.) Marital status is imputed for people who did not respond to this question on the census form.

Step 2.

2.26. Net undercount rates derived from the Post-Enumeration Survey for total (not disaggregated by age) males and total females in each marital status category, are applied to the totals of the census counts in Step 1 to obtain adjusted census counts of total males and females for each marital status.

Step 3.

2.27. Australian residents temporarily overseas on census night by sex for each marital status are added to the adjusted census counts derived in Step 2 to give census date marital status population totals.

Step 4.

2.28. Using an iterative proportionate fitting procedure (see Appendix 2), the census counts of residents by single years of age and sex for each marital status in Step 1 are forced to add to the adjusted totals derived in Step 3, while simultaneously forced to add to the census date population estimates of all residents by age and sex as described above (see paragraph 2.12 in the previous topic).

Step 5.

2.29. If the census does not fall on 30 June, a further adjustment is necessary to produce estimates as at the nearest 30 June reference date. For example, the 1996 Census was held on 6 August, and after Steps 1 to 4 were finalised the population estimates at 6 August had to be back-dated to 30 June. This was accomplished using birth and death registrations and overseas arrivals and departures data for the period 1 July to 6 August.

2.30. For 30 June estimates in census years only, population estimates by marital status, age and sex are also cross-classified by state. This is achieved by forcing census counts to add up to the estimated resident population by age, sex and state, while simultaneously forcing them to add to the estimated resident population by marital status, age and sex. Post-censal marital status estimates by state are not available as there is no reliable information on interstate migration by marital status.

Post-censal estimates by marital status

2.31. Until 30 June 1998, marital status estimates by age for post-censal years have been compiled quarterly by updating the census year estimates according to changes to the overall size of the population resulting from births, deaths and overseas migration, as well as changes in the marital status category of the existing population due to marriage, divorce, and death of spouse.

2.32. Annual population estimates by marital status have not been available for post-censal years since 30 June 1998 because the removal of the marital status questions on the overseas arrival and departure cards from 1 July 1998 onwards has prevented reliable estimation of overseas migration by marital status.

2.33. Each component of change is first converted to financial year of birth in order to match events with the corresponding population birth cohorts. The population for each marital status for each birth cohort is then updated as follows:

2.35. Population estimates by country of birth are also compiled quarterly and published annually as at 30 June for Australia as a whole. These estimates, which are by single years of age and sex, classify the population according to over 60 countries of birth. Population estimates by country of birth at the census date are compiled as follows:

Census date population estimates by country of birth

Step 1.

2.36. Census counts of residents are compiled by single years of age and sex for each country of birth. ('Census counts of residents' necessarily means that overseas visitors who are counted in the census are excluded). Country of birth is imputed for those people who did not respond to this question on the census form.

Step 2.

2.37. Net undercount rates are derived from the Post-Enumeration Survey for total (not disaggregated by age) males and females classified into twelve groups of countries of birth. Undercount rates are assumed to be the same for each country within a group. These rates are applied to the totals of the census counts in Step 1 to obtain adjusted total census counts of males and females by country of birth.

Step 3.

2.38. Australian residents temporarily overseas on census night, by sex and twelve country of birth groups are added to the adjusted census counts derived in Step 2 to give census date country of birth population totals.

Step 4.

2.39. Census counts of residents by single years of age and sex for each country of birth in Step 1 are prorated to add to the population totals derived in Step 3.

Step 5.

2.40. Data from Step 4 are converted to financial year of birth then forced to add to the census date population estimates of all residents by financial year of birth and sex (as described in paragraph 2.12 of the previous topic).

Step 6.

2.41. If the census does not fall on 30 June, a further adjustment is necessary to produce estimates as at the nearest 30 June reference date. For example, the 1996 Census was held on 6 August, and after Steps 1 to 5 were finalised the population estimates at 6 August had to be back-dated to 30 June. This was accomplished using data on births and deaths registrations and overseas arrivals and departures for the period 1 July-6 August.

2.42. For 30 June estimates in census years only, population estimates by country of birth, age and sex are also cross-classified by state. This is achieved by forcing census counts to add up to the estimated resident population by age, sex and state, while simultaneously forcing them to add to the estimated resident population by country of birth, age and sex. Post-censal country of birth estimates by state are not available as there is no reliable data on interstate migration by country of birth.

Post-censal estimates by country of birth

2.43. Population estimates by country of birth for post-censal years are compiled quarterly by updating the census year estimates in accordance with births, deaths and overseas migration. Each component of change is first converted to financial year of birth. The population for each country of birth by birth cohort are then updated as follows:

	For the Australian-born population Pat = Pat-1 + Bt - Dat + Oat
	For all other countries of birth Pbt = Pbt-1 - Dbt + Obt
	where:
	Pbt	=	population at end of quarter t born in country b
	Bt	=	births in quarter t
	Dbt	=	deaths in quarter t of persons born in country b
	Obt	=	net overseas migration in quarter t of persons born in country b

2.44. Annual estimates of the Indigenous (Aboriginal and Torres Strait Islander) population by age (in five year groups) and sex for the States and Australia have been compiled for the years 1986 to 1996. The estimates are 'experimental' in that the standard approach to population estimation is not possible because satisfactory data on births, deaths, overseas and internal migration are not generally available. Furthermore, there is significant intercensal volatility in census counts of the Indigenous population, thus adding to the problem of estimating the true Indigenous population. This volatility can in part be attributed to the change in propensity for persons to be identified as Indigenous as recorded on a census forms.

2.45. The experimental estimates for 1991 to 1996 used as their starting point the place of usual residence census count as at 6 August 1996, adjusted for persons recorded as Indigenous whose parents were born overseas, non-response to the Aboriginal/Torres Strait Islander origin question in the census, net census undercount and registered Indigenous births. These 6 August Indigenous estimates were then 'survived' back to 30 June 1996 and then back to 30 June 1991 using life tables. This method is known as the reverse survival method and assumed zero net internal and zero overseas migration. This is described in greater detail in Appendix 5 - Estimating the Indigenous Population.