Peer-Reviewed Journal Details
Mandatory Fields
Donal O'Neill and Olive Sweetman
2016
May
Empirical Economics
Bounding obesity rates in the presence of self-reporting errors
Published
()
Optional Fields
obesity, measurement error, bounds
50
3
857
871
We examine what, if anything, we can learn about obesity rates using self-reported BMI once we allow for possible measurement error. We use self-reported obesity rates, along with estimates of misclassification rates, to derive upper and lower bounds for the true population obesity rate. These bounds are then used as the basis for obesity rankings. Our results show, that once measurement error is taken into account, it is difficult to obtain meaningful rankings across European countries. However, our analysis shows that it is still possible to rank US states by obesity status using only minimal assumptions on the nature of the error process. As a result, cross-state variation in self-reported BMI, when used in conjunction with our bounds, may still provide a useful source of information for understanding the causes and consequences of obesity in the USA.
Springer Berlin
https://doi.org/10.1007/s00181-015-0958-
Grant Details