要旨：　In the evaluation of social programs, it is often difficult to conduct randomized controlled experiments due to non-compliance; therefore the local average treatment effect (LATE) is commonly applied. However, the LATE identifies the average treatment effect only for a subpopulation known as compliers and requires the monotonicity assumption. Given these limitations of the LATE, this paper proposes a nonparametric strategy to identify the causal effects for larger populations (such as the ATT and ATE) and to remove the monotonicity assumption in the cases of non-compliance. Our strategy utilizes two types of auxiliary observations, one is an outcome before assignment and the other is a treatment before assignment. These observations do not require specially designed experiments, and are likely to be observed in baseline surveys of the standard experiment or panel data. We show the results for the random assignment and those of multiply robust representations in the case where the random assignment is violated. We then present details of the GMM estimation and testing methods which utilize over-identified restrictions. The proposed strategy is illustrated by empirical examples which revisit the studies by Thornton (2008), Gerber et al. (2009), and Beam (2016), as well as the data set from the Oregon Health Insurance Experiment and that from an experimental data on marketing in a private sector.

【Paper】

Abstract：Existing empirical research in economics on neighborhood racial sorting is overwhelmingly premised on the idea that racial preferences for a location depend on the racial shares in that location, without considering potential spatial spillover effects from nearby areas. Does this matter for the way we view the cross-section and dynamics of racial neighborhood segregation? We nest Schelling (1971)’s bounded neighborhood and spatial proximity theories within a discrete choice model, where the key distinction is precisely such spatial spillovers. We simulate the model and examine the data for 1970-2000 for more than 100 U.S. metros. Two features of the data are most compelling: the powerful presence of racial clusters and the fact that drastic racial change is concentrated at the boundary of these clusters. Both point to the spatial proximity model as the proper foundation for a theory of racial neighborhood evolution. We use these insights to revisit prominent results on racial tipping where our theory guides us to distinguish differences by location. While prior research pointed to powerful racial tipping in the form of White exit, we show this is largely driven by theoretically-distinct “biased white suburbanization” leading to White entry in remote areas. In urban areas far from existing Minority clusters, we find zero or small tipping effects, at odds with a bounded neighborhood interpretation. The most consistent effects of tipping, still of modest size, are found in areas adjacent to existing Minority clusters, confirming the relevance of the racial spillovers of the spatial proximity model. Existing research conflates these quite distinct effects. Overall, our results suggests that tipping is a less central feature of racial neighborhood change than suggested in prior research and that greater attention needs to be paid to spatial dimensions of the problem.

要旨：This paper examines the optimal design of retirement policies that rely on private insurance markets while accounting for financial frictions within these markets. We analyze the impact of uninsurable aggregate interest rate shocks in a life-cycle model where the government screens productivity, longevity, and altruism. We show that observing retirees’ annuitization choices helps separate individual types. However, private annuity markets face supply-side inefficiencies due to interest rate risk. To improve market efficiency, the government can issue long-term bonds, supported by interest rate-contingent taxes. Therefore, full privatization can only be optimal without interest rate shocks; otherwise, Social Security remains necessary.