Identification With Additively Separable Heterogeneity
研究一类潜在效用模型，其中不可观测异质性具有可加可分形式，在独立性假设下，仅利用平均需求即可识别回归变量对商品吸引力的影响，并无需指定异质性分布即可识别平均间接效用（福利）。
This paper provides nonparametric identification results for a class of latent utility models with additively separable unobservable heterogeneity. These results apply to existing models of discrete choice, bundles, decisions under uncertainty, and matching. Under an independence assumption, such models admit a representative agent. As a result, we can identify how regressors alter the desirability of goods using only average demands. Moreover, average indirect utility (“welfare”) is identified without needing to specify or identify the distribution of unobservable heterogeneity.