Three Essays On Generalized Method Of Moments

Generalized Method of Moments (GMM) has become one of the main statistical tools for the analysis of economic and financial data. This book is the first to provide an intuitive introduction to the method combined with a unified treatment of GMM statistical theory and a survey of recentimportant developments in the field. Providing a comprehensive treatment of GMM estimation and inference, it is designed as a resource for both the theory and practice of GMM: it discusses and proves formally all the main statistical results, and illustrates all inference techniques using empiricalexamples in macroeconomics and finance.Building from the instrumental variables estimator in static linear models, it presents the asymptotic statistical theory of GMM in nonlinear dynamic models. Within this framework it covers classical results on estimation and inference techniques, such as the overidentifying restrictions test andtests of structural stability, and reviews the finite sample performance of these inference methods. And it discusses in detail recent developments on covariance matrix estimation, the impact of model misspecification, moment selection, the use of the bootstrap, and weak instrumentasymptotics.

This thesis consists of three essays on international finance. The first essay is "Exchange rates and Fundamentals". A new open interest rate parity condition that takes account of economic fundamentals is developed from stochastic discount factors (SDFs) of two countries. Through this parity condition, business cycles or fundamentals are linked to exchange rates. Key empirical findings from this parity condition are as follows. First, this model beats the random walk hypothesis: economic fundamentals explain exchange rate movements for high interest rate currencies. Exchange rates of low interest rate currencies act like a random walk because they are less correlated with fundamentals owing to their low risk. For example, U.S. business cycles explain the direction of changes in exchange rates against the dollar. The same thing is true for Japan. Second, this model resolves the forward premium puzzle: the forward premium puzzle is not a general characteristic as regarded in previous studies. It happens when the risk awareness of investors is low, during economic expansions and for low risk currencies. The second essay is "Carry Trade and Global Financial Instability". Carry trade, an opportunistic investment strategy that takes advantage of interest rate differential across countries, is identified the cause of the large-scale depreciations of peripheral currencies in the later half of 2008. A simultaneous equations model, which is derived from a conceptual partial equilibrium model for a local foreign exchange market, is estimated from a cross-sectional sample. The results suggest that the larger appreciation of the yen than the dollar was brought about by a lack of the local supply of the yen rather than a more severe crunch of yen credits. The third essay is "The Economic Origin of Letters of Credit". This essay discusses the economic origin of letters of credit, an instrument widely used in international trade. A game theoretical analysis shows that letters of credit improve efficiency in trade settlements, increasing returns in trade. A few notable facts on letters of credit are discussed. First, the new institution is adopted by merchant banks to maximize their profits and in the process, an improvement in efficiency of international transactions is obtained. Second, the organization established by the legacy institution, bills of exchange, played a critical role in adopting the new institution. Third, the legal enforcement is not essential in this economic institution. Finally, two drivers are identified that improve efficiency of transactions: concentration and projection.

This dissertation consists of three essays, first two of which consider a new estimation method of dynamic panel data models and the last one considers an application of these models. The first essay (Chapter 1) offers empirical likelihood (EL) estimation of dynamic panel data models, which provide great flexibility to empirical researchers. EL estimation method is shown to have great advantages in usual settings, however little is known on the relative merits of these estimators in panel data models. With this essay, we try to fill that gap by establishing the asymptotic properties of the EL estimator for a dynamic panel model with individual effects when both the time and the cross-section dimensions tend to infinity. We give the conditions under which this estimator is consistent and asymptotically normal. In the second essay (Chapter 2), via a Monte Carlo study, we assess the relative finite sample performances of EL, generalized method of moments, and limited information maximum likelihood estimators for an autoregressive panel data model when there are many moment conditions. We also extend our results to the many weak moments settings. Our results suggest that when the overall performances are concerned, in terms of median, interquartile range and median absolute error of the estimators, in both strong and weak moments settings, EL is more reliable. In the final essay (Chapter 3) we consider an application of dynamic panel data models to examine the determinants of the allocation of state highway funds using panel data for North Carolina's 100 counties for the years 1990 to 2005. We make two main contributions with this essay. First, although there have been numerous studies of highway funding at the state level, to our knowledge, there is no analysis at the sub-state or county levels. Second, by using dynamic panel data models and sophisticated methods to estimate them, we account for any potential persistence in the process of adjustment toward an equilibri.