"Food survey data all wrong?" This was the headline of a newspaper article on a report from the from the General Accounting Office of the U.S. Government related to the Nationwide Food Consumption Survey. The survey of 6,000 household of all incomes and 3,600 low-income households is intended to be the leading authority on who consumes what foods. Even though the original household were randomly selected, the GAO said the result were questionable because only 34% of the sampled household responded. Do you agree? What is the nature of the biases that could be caused by the low response rate? (The article was printed in the Gainesville Sun, September 11, 1991)