Show simple item record

dc.contributor.advisorBarnett, William A
dc.contributor.authorHan, Qing
dc.date.accessioned2020-01-17T21:58:31Z
dc.date.available2020-01-17T21:58:31Z
dc.date.issued2019-05-31
dc.date.submitted2019
dc.identifier.otherhttp://dissertations.umi.com/ku:16536
dc.identifier.urihttp://hdl.handle.net/1808/29880
dc.description.abstractThis dissertation considers monetary services aggregation theory in Macroeconomics, the nonparametric approaches in Econometrics with censoring data and endogenous variables, and the macroeconomic dynamic modelling. It contributes to the current literature in three ways. First, it extends the monetary aggregation theory to incorporate Knightian uncertainty by using a non-additive probability measure. Our aggregation theory under uncertainty nests the previous literature of the perfect certainty and/or risky cases. Second, we consider a nonparametric estimation of a censoring data model with endogenous variables and transform the problem into a nonparametric LAD additive model for estimation and testing. Third, in the open economy literature, the high consumption correlation among different countries is a stubborn anomaly. We establish an open economy Dynamic Stochastic General Equilibrium (DSGE) model that successfully solves this problem. The model must feature asymmetric preference, incomplete financial markets, and terms of trade shocks at the same time. The first part considers monetary aggregation under uncertainty aversion (perhaps under risk aversion as well). The presence of uncertainty and the agent's attitude towards it are represented by a nonadditive probability measure. The major findings are three-fold: first, the user cost of monetary assets under uncertainty aversion produces useful boundaries. We no longer have covariances, instead, we have inequalities, and our model nests some of the previously derived results. Second, deviating from expected utility does not exclude the existence of a user-cost solution which is analogous to the expected utility representation, but that is only a special case. Third, under Choquet expectation the user costs have an interval within which no trade of monetary assets will occur, such an effect depends solely on uncertainty aversion, not on risk aversion. The second paper deals with the problem of nonparametric estimation using censored data in a model that features endogeneity. Nonparametrics with endogenous variables is difficult to handle because of ill-posed inverse problem. Nonparametrics with censoring does not attract the attention as it deserves because people are inclined to resort to quantile estimation when data is censored. We stick to the nonparametric estimation under two mild conditions. It is the endogeneity that shapes the model to be additive, and it is because of censoring the model is reduced to a (nonparametric) LAD estimation under the assumption of conditional zero median of the error term. This paper therefore transforms the problem into a Nonparametric Additive Least Absolute Deviation estimation which is saliently more robust than L₂ norm estimation. We establish the asymptotic normality of the estimated unknown functions. The estimation and inference are easy to carry out. The third paper establishes a dynamic stochastic general equilibrium model of the Chinese open real economy and aims to give a theoretical account of the empirical stylized facts of economic volatility. Specifically, we investigate two questions: first, what are the stylized facts of the Chinese open economy fluctuation? Is there anything that makes it different from other major economies? Secondly, could theoretical models reasonably explain and fit those facts well? To answer the first question, we use four different filters to extract volatility to contribute a robust summary of the stylized facts. As for the second question, we find that asymmetric preference, incomplete financial markets and terms of trade shocks significantly improve the model’s prediction. Negative international co-movement of investment is the special feature of the Chinese economy, and our model caters for that well.
dc.format.extent82 pages
dc.language.isoen
dc.publisherUniversity of Kansas
dc.rightsCopyright held by the author.
dc.subjectEconomics
dc.subjectCensoring Data
dc.subjectChoquet Expectation
dc.subjectEndogeneity
dc.subjectGeneral Equilibrium
dc.subjectMonetary Aggregation
dc.subjectNonparametrics
dc.titleThree Papers on Monetary Aggregation under Knightian Uncertainty, Kernel Estimation, and Dynamic Modelling
dc.typeDissertation
dc.contributor.cmtememberCai, Zongwu
dc.contributor.cmtememberPasik-Duncan, Bozenna
dc.contributor.cmtememberKeating, John
dc.contributor.cmtememberZhang, Jianbo
dc.thesis.degreeDisciplineEconomics
dc.thesis.degreeLevelPh.D.
dc.identifier.orcidhttps://orcid.org/0000-0001-5926-9950
dc.rights.accessrightsopenAccess


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record