Identication of Expected Outcomes in a Data Error Mixing Model with Multiplicative Mean Independence

We consider the problem of identifying a mean outcome in corrupt sampling where the observed outcome is drawn from a mixture of the distribution of interest and another distribution. Relaxing the contaminated sampling assumption that the outcome is statistically independent of the mixing process, we assess the identifying power of an assumption that the conditional means of the distributions di¤er by a factor of proportionality. For binary outcomes, we consider the special case that all draws from the alternative distribution are erroneous. We illustrate how these models can inform researchers about illicit drug use in the presence of reporting errors. Keywords: contaminated sampling, corrupt sampling, measurement error, partial identi…cation, nonparametric bounds JEL codes: C1, C10, C14, I12 The authors received valuable comments from an anonymous referee, the editor, an associate editor, Phil Cross, Francesca Molinari, Steve Stern, and seminar participants at Georgetown University, Iowa State University, and the University of Virginia. They also bene…ted from discussions at meetings of the Econometric Society and the Southern Economic Association. This research was supported in part by the Bankard Fund for Political Economy.