Economic models often involve non-separability between observed and unobserved<br/> heterogeneous characteristics of economic agents. This dissertation presents methods<br/> of identification, estimation, and inference of nonparametric and nonseparable economic<br/> models for cross section and panel data. The first chapter discusses identification<br/> and estimation of nonseparable dynamic panel data with non-random dynamic<br/> selection. It shows that nonseparable dynamic panel models with endogenous attrition<br/> can be identified from six time periods of unbalanced panel data. The principle<br/> of constrained maximum likelihood is proposed for consistent estimation. The second<br/> chapter discusses identification of average structural partial effects for endogenous<br/> nonseparable cross-section models without assuming monotonicity. Nonparametric<br/> identification methods are proposed for various first-stage structural and reducedform<br/> assumptions. The third chapter discusses statistical methods of model tests<br/> for endogenous nonseparable cross-section models when instruments exhibit discrete<br/> variations and the outcome structure is not monotone with respect to unobserved heterogeneity. It shows that the testing method possesses sufficient power even if<br/> instruments are discrete and exert only local effects on endogenous choice.
Sasaki, Yuya,
"Essays in Econometrics of Heterogeneous Agents"
(2012).
Economics Theses and Dissertations.
Brown Digital Repository. Brown University Library.
https://doi.org/10.7301/Z06W98D0