How Likely to Be Caught: Identification and Estimation of Strategic Misreporting

Assistant Professor, Department of Economics, Tsinghua University.

Prof. Shengjie Hong's CV 

Data of self-reported variables are prone to measurement errors due to misreporting behaviors. We consider economic environments where the self-reporting behavior is determined by: 1) The payoff structure, i.e., benefits from misreporting and penalties; and 2) The detection rate, i.e., the probability of being caught for misreporting. Under regularity conditions, we achieve nonparametric identification of the detection rate function, and proposed a three-step procedure to consistently estimation it. A desirable feature of our methods is that they do not rely on the specification of the payoff structure. As an empirical illustration, we apply our methods to study financial fraudulent reporting in China.