Palloni, Alberto, and Jason R. Thomas
Working paper no. 2011-09
Abstract
Assessing the impact that socioeconomic determinants have on the prevalence of certain chronic conditions reported by respondents in population surveys must confront two problems. The first is that the self-reports could be in error (false positives and false negatives). The second is that those reporting are a selected sample of those who ever experience the problem, the selection being heavily influenced by excess mortality due to the condition being reported. In this paper, we use a combination of empirical data and microsimulation to (a) assess the magnitude of the biases due to the selection problem, and (b) suggest adjustment procedures that correct for biases.