ADJUSTMENT OF REPORTED PREVALENCE OF RESPIRATORY SYMPTOMS FOR NONRESPONSE IN A MULTICENTER HEALTH SURVEY

Background. Estimation of non-response bias by modelling prevalence as a function of the number of mailings required to achieve a response, or of the cumulative response, has been advocated, but the models have not incorporated age and sex, differential response rates by age and sex, or season of response. Methods. The effect on age-sex standardize d prevalence of estimating non-response bias using a variety of models was investigated using data on nine symptom and medication questions from 13 007 subjects in the three English centres of the European Comm unity Respiratory Health Survey. Comparison was made of goodness of fi t and the prediction of responses in a 25% follow-up sample with the o bserved values. Results. Despite low response rates in Cambridge and s ignificant decreases in prevalence with additional mailings or increas ing cumulative response in Norwich, there were only small effects on e stimated age-sex standardized prevalences. No model was consistently b etter for any centre or question. Conclusions. The models are useful f or exploring the sensitivity of estimated prevalence to non-response b ias, but should be used with caution to adjust estimates. Ideally firs t mailings should be staggered over the whole year so that mailing and season are not confounded, and sufficient mailings or other contacts carried out for the whole sample to ensure a high response rate.