|Page tools: Print Page Print All|
To date the Australian Bureau of Statistics lacks a consistent and reliable set of methods to model design effects from past survey data in order to assess the sampling error properties of proposed household surveys. This paper articulates the key challenges in modelling robust design effects for household surveys and examines general solutions in the context of two recent sample design applications. Advice is sought from the Methodology Advisory Committee as to the suitability of these solutions as standard methods for ongoing and future application.
These documents will be presented in a new window.