A COMMENT ON “ESTIMATING DYNAMIC DISCRETE CHOICE MODELS WITH HYPERBOLIC DISCOUNTING” BY HANMING FANG AND YANG WANG
指出范汉明和王洋(2015)的命题2声称在排除限制下双曲贴现动态离散选择模型具有一般识别，但该命题使用的“一般”定义不排除模型处处不可识别，且证明有误，因此该命题对模型识别无意义。
Abstract Fang and Wang's (2015) Proposition 2 claims generic identification of a dynamic discrete choice model with hyperbolic discounting under exclusion restrictions. We note that Proposition 2 uses a definition of “generic” that does not preclude that a generically identified model is nowhere identified. We provide two examples of models that are generically identified under this definition, but that are, respectively, everywhere and nowhere identified. We then show that the proof of Proposition 2 is incorrect and incomplete. We conclude that Proposition 2 has no implications for identification of the dynamic discrete choice model and suggest alternative approaches to its identification.