3302.0.55.004 - Information Paper: Death registrations to Census linkage project - Methodology and Quality Assessment, 2011-2012  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 18/09/2013  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All  
Contents >> Introduction

INTRODUCTION

The most recent cycle of the Death registrations to Census linkage project (otherwise referred to as the Indigenous Mortality Project) was conducted as part of the 2011 Census Data Enhancement (CDE) program. The CDE program included a number of linkage projects that brought together data from the 2011 Census of Population and Housing with other specified datasets. This project involved linking the Census with death registrations to examine differences in the reporting of Indigenous status across the two datasets in order to apply adjustment factors to mortality and life-expectancy estimates. See also Census Data Enhancement Project: An Update, October 2010 (cat. no. 2062.0).

This information paper is the first of three reports from the Indigenous Mortality project. It describes the methodology and quality features implemented in the process and presents an assessment of linkage quality. Adjusted mortality rates for the Aboriginal and Torres Strait Islander population together with 2011 Census-based life expectancy estimates will be released in Life Tables for Aboriginal and Torres Strait Islander Australians (cat. no. 3302.0.55.003) on 15 November 2013. At that time, Death registrations to Census linkage project - Key Findings for Aboriginal and Torres Strait Islander peoples, 2011-12 (cat. no. 3302.0.55.005)—an examination of social and demographic characteristics associated with differences in Indigenous status identification between the two datasets —will also be released.

This project linked 20,928,304 records from the 2011 Census with 153,455 death registrations where the death occurred between the 10th of August 2011 and the 27th of September 2012 inclusive. The time period of death registrations was selected in order to capture as many deaths as possible of people who were counted in the 2011 Census (which took place on the 9th of August 2011). Due to lags between occurrence and registration, the number of deaths registered during this period would be lower than the number of deaths that occurred, particularly for those deaths occurring towards the end of the reference period.

The 2011 Census processing period, like the 2006 Census, provided the opportunity to link deaths with the full Census using name, address and other variables common to both datasets. This is referred to by the ABS as a Gold linkage method. It should be noted that all names and addresses collected in the Census were destroyed at the conclusion of Census processing on 7 December 2012, setting an end point to the Gold linkage period.

In detail, the aims of this project were to:

    • assess the consistency of Indigenous status as reported in death registration and Census data
    • estimate measures of undercoverage of deaths of Aboriginal and Torres Strait Islander people by state/territory and remoteness areas of Australia
    • investigate the feasibility of applying adjustment factors for Aboriginal and Torres Strait Islander deaths output data
    • provide input into the compilation of life tables for Aboriginal and Torres Strait Islander people, life expectancy estimates and Aboriginal and Torres Strait Islander/non-Indigenous differences in life expectancy and other mortality measures that are consistent with population estimates based on the adjusted 2011 Census of Population and Housing.

The 2011 Death registrations to Census linkage project expanded on the methods used in the 2006 cycle as described in the research paper Linking Census Records to Death Registrations (cat. no. 1351.0.55.030). The main enhancements implemented for the 2011 project included:
    • improvements to linking software and hardware
    • improvements to data cleaning and standardisation – particularly names
    • refinements to the blocking and linking strategy
    • use of the Expectation-Maximisation algorithm for estimating linkage model parameters
    • increased and targeted clerical review on record pairs where the death registration was for a person identified as being of Aboriginal and Torres Strait Islander descent.


Previous PageNext Page