APPENDIX 1 - USING INDIGENOUS CENSUS DATA
INTRODUCTION
This appendix presents a set of guidelines concerning the use of Census data about Indigenous Australians. The guidelines were prepared and widely circulated following a workshop held on this topic in early 1998, and published by the ABS in February 1999 in Occasional Paper: Population Issues, Indigenous Australians, 1996 (cat. no. 4708.0). They should be attributed to the 1998 Working Group to Establish Guidelines for Interpreting Indigenous Census Data.
GUIDELINES FOR INTERPRETING INDIGENOUS CENSUS DATA
Guiding principles
It is not possible to construct a set of tight and specific guidelines which, if followed by users, would indicate how to make valid comparisons between Censuses with respect to Indigenous statistics. There is no prescription which will provide guaranteed protection against making inappropriate interpretations. However, a few guiding principles may be of assistance to users.
User beware
Any Indigenous statistical comparisons made between two Censuses must be made with caution and should not be accepted at face value until the user has explored, to his/her satisfaction, the possibility that the differences might be solely or largely a consequence of non-demographic increase in Census counts. Users might otherwise draw incorrect conclusions about whether changes in social conditions have occurred.
Use percentages
Users should present their statistical estimates as percentages where both numerator and denominator data are from the same Census. Analyses of intercensal statistical differences should be made by comparing percentages from two Censuses, rather than directly comparing counts or numbers. In most instances appropriate percentages will be less biased than the numerator and denominator counts. In particular, percentages are estimated without bias, if the bias in the counts is the same in percentage terms for the numerator and denominator.
Use specific geography
Any analysis conducted on data pertaining to all Indigenous peoples in Australia and undertaken to detect changes between Censuses may be subject to biases if the variable of interest displays significantly different patterns for urban and remote areas. The bias results from changing patterns across geography or the propensity to be identified as Indigenous in the Census. Biases may be reduced considerably for analyses which are restricted to remote geographical regions where the changes in Indigenous population counts between Censuses can be largely explained in standard demographic terms.
Consider household size and composition
Factors which might be associated with household size and composition (i.e. the proportion of Indigenous and non-Indigenous peoples in the household) should be treated with the same caution as geographical variations.
Consider your population
When using Indigenous population figures, users should ensure they have the most appropriate set of numbers for their purposes.