8176.2.55.001 - Experimental Estimates of Employees by Industry and Workplace Location, Victoria, 2005-06 to 2010-11 Quality Declaration 
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 05/12/2012  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All  
Contents >> Geocoding Process

GEOCODING PROCESS

In order to produce the experimental estimates at the Local Government Area (LGA) level, each workplace address supplied to the ABS in the WorkSafe and Self-Insurer datasets, as well as the Comcare insured workplace locations obtained from the ABS Business Register were geocoded.

AUSTRALIAN STATISTICAL GEOGRAPHY STANDARD

The Australian Statistical Geography Standard (ASGS) is the new geographical framework used by the ABS. It brings together all regions for which the ABS publishes statistics within one framework and is used for the collection and dissemination of geographically classified statistics.

These experimental estimates are output at the Victorian LGA level. LGAs are part of the ASGS non-ABS structure. Non-ABS structures are hierarchies of regions that are not defined or maintained by the ABS. LGAs are defined by the Departments of Local Government, or their equivalent in each state or territory, excepting the Australian Capital Territory.

All business addresses geocoded to produce the experimental estimates were coded to 2011 ASGS LGA boundaries, and thus the LGA boundaries in this publication are comparable across all financial years.

More information on the ASGS can be found at www.abs.gov.au/geography.

GEOCODING SCOPE AND RESULTS

Workplace locations were geocoded by the ABS using address coding software. Approximately 91% of the addresses were acceptably coded to a 2011 ASGS LGA. The remaining 9% of addresses could not be confidently assigned to an LGA and manual intervention was required in order to code these workplace locations to their relevant LGA.

As the number of WorkSafe workplace locations requiring manual intervention was quite large, a weighting was applied to these outstanding addresses. The weighting enabled ABS to identify the workplace locations which made a significant contribution to the employment and remuneration size of their industry sub-division and these significant contributors were then manually coded to an LGA.

The remaining less-significant WorkSafe workplace locations were assigned to an LGA using an imputation method based on post codes.

Due to the small number of Self-Insurer and Comcare workplace locations which could not be confidently coded to an LGA using the address coding software, all outstanding addresses in these data sets were manually coded to an LGA.

ADDRESSES IMPUTED BY POSTCODE

Addresses which did not return any LGA information from the address coder software were imputed using a donor post code. These donor post codes were obtained by randomly selecting an automatically geocoded workplace location with the same post code as the location being imputed.

This process ensured workplace locations have the same distribution across LGAs as the automatically and manually coded units, which means the workplace locations were imputed based on business location rather than a weighting method based on the population and people.



Previous PageNext Page