The theory and econometrics of health information in cross-sectional nutrient demand analysis

Understanding the role of health information in food and nutrient demand ha s become an important issue over the last decade. Endogeneity and measureme nt error are two empirical problems that are inherent in this type of analy sis. While some type of instrumental variables estimation would appear the obvious solution, this article provides several theoretical and empirical r easons why this is not the case in cross-sectional analysis. An alternative estimation strategy is pursued, an empirical example is given, and the imp lications are discussed.