Methodological Research
Improving the design of health surveys

Background

Methodological research is being undertaken to improve survey design as it relates to the collection of health and economic date. Including:

An examination of why respondents alter their response when asked two self-reported health status questions in the course of same health survey and the consequences for health inequality measurement (see below);
Using regression methods to correct for reporting bias in self-reported health surveys;
Developing statistical techniques to determine the optimal recall period over which health service use questions are asked (e.g.
How many times have you been to the Doctor in the last X months?);
Undertaking empirical research to understand how recall error varies over time using a randomized trial of question with different recall periods;
Quantify the effect on health inequality measures from grouping income data into ranges.

Part of this research is currently supported by from an unrestricted grant from Servier Australia.

Clarke P. and Ryan C. Self-reported health: reliability and consequences for health inequality measurement, Health Economics, 2006, 15: 645-652.