Three Essays on More Powerful Cointegration Tests PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Three Essays on More Powerful Cointegration Tests PDF full book. Access full book title Three Essays on More Powerful Cointegration Tests by Hyejin Lee. Download full books in PDF and EPUB format.
Author: Hyejin Lee Publisher: ISBN: Category : Electronic dissertations Languages : en Pages : 102
Book Description
The main focus of this dissertation is to find ways to improve the power in cointegration tests. This dissertation consists of three essays. In the first essay, a modified testing procedure for the Engle and Granger (1987; EG) cointegration test is suggested. Specifically, we suggest augmenting the usual EG testing regression with the first difference of the integrated regressors. The limiting distribution of this modified EG test under the null hypothesis will depend on the nuisance parameter, which reflects the signal-to-noise ratio. This essay shows that the nuisance parameter issue can be resolved when we follow the asymptotic distribution of the modified EG test, and use the relevant new sets of critical values corresponding to the estimated value of the nuisance parameter. It is found that the size and power properties of the modified EG test are fairly good. The modified EG test gains improved power rather than losing power as the signal-to-noise ratio increases. In the second essay, we examine whether non-linear unit root tests is robust with non-normal errors, which provides a motivation for the third essay. Especially, the second essay demonstrates how popular nonlinear unit root tests perform in the presence of non-normal errors. Non-normal errors normally do not pose a problem in usual linear unit root tests since the least squares estimator will still be the most efficient under certain ideal conditions regardless of normal or non-normal errors. The asymptotic properties of the popular linear Dickey-Fuller tests, for example, will be unaffected by non-normal errors. As such, the literature has not paid much attention to this issue. Nevertheless, whether similar results will carry over to nonlinear unit root tests with non-normal errors is a question that merits examination. To our surprise, the extant literature on nonlinear unit root tests has not examined this important question. We find that, in general, nonlinear unit root tests will suffer a loss of power in the presence of non-normal errors. In this regard, this essay brings out the neglected point that the obvious analogies of linear processes do not necessarily hold for nonlinear models. The third essay suggests new cointegration tests that are more powerful in the presence of non-normal errors. We use a two-step procedure based on the "residual augmented least squares" (RALS) method to make use of nonlinear moment conditions driven by non-normal errors. By utilizing this neglected information, we can make the existing tests more powerful. The suggested testing procedure is easy to implement. The underlying idea is similar to adding stationary covariates to improve the power of the test, but the suggested procedure does not require any new covariates outside the system. Instead, we can exploit the information on the non-normal error distribution that is already available but ignored in the usual cointegration tests. Our simulation results show significant power gains over existing cointegration tests.
Author: Hyejin Lee Publisher: ISBN: Category : Electronic dissertations Languages : en Pages : 102
Book Description
The main focus of this dissertation is to find ways to improve the power in cointegration tests. This dissertation consists of three essays. In the first essay, a modified testing procedure for the Engle and Granger (1987; EG) cointegration test is suggested. Specifically, we suggest augmenting the usual EG testing regression with the first difference of the integrated regressors. The limiting distribution of this modified EG test under the null hypothesis will depend on the nuisance parameter, which reflects the signal-to-noise ratio. This essay shows that the nuisance parameter issue can be resolved when we follow the asymptotic distribution of the modified EG test, and use the relevant new sets of critical values corresponding to the estimated value of the nuisance parameter. It is found that the size and power properties of the modified EG test are fairly good. The modified EG test gains improved power rather than losing power as the signal-to-noise ratio increases. In the second essay, we examine whether non-linear unit root tests is robust with non-normal errors, which provides a motivation for the third essay. Especially, the second essay demonstrates how popular nonlinear unit root tests perform in the presence of non-normal errors. Non-normal errors normally do not pose a problem in usual linear unit root tests since the least squares estimator will still be the most efficient under certain ideal conditions regardless of normal or non-normal errors. The asymptotic properties of the popular linear Dickey-Fuller tests, for example, will be unaffected by non-normal errors. As such, the literature has not paid much attention to this issue. Nevertheless, whether similar results will carry over to nonlinear unit root tests with non-normal errors is a question that merits examination. To our surprise, the extant literature on nonlinear unit root tests has not examined this important question. We find that, in general, nonlinear unit root tests will suffer a loss of power in the presence of non-normal errors. In this regard, this essay brings out the neglected point that the obvious analogies of linear processes do not necessarily hold for nonlinear models. The third essay suggests new cointegration tests that are more powerful in the presence of non-normal errors. We use a two-step procedure based on the "residual augmented least squares" (RALS) method to make use of nonlinear moment conditions driven by non-normal errors. By utilizing this neglected information, we can make the existing tests more powerful. The suggested testing procedure is easy to implement. The underlying idea is similar to adding stationary covariates to improve the power of the test, but the suggested procedure does not require any new covariates outside the system. Instead, we can exploit the information on the non-normal error distribution that is already available but ignored in the usual cointegration tests. Our simulation results show significant power gains over existing cointegration tests.
Author: Yan Lu Publisher: ISBN: Category : Electronic dissertations Languages : en Pages : 115
Book Description
The first essay extends the pioneering cointegration test of Johansen (1991) to allow for structural breaks in a cointegration system. Instead of using usual dummy variables, we utilize a Fourier function to control for an unknown number of multiple breaks in the cointegration system. When we use dummy variables, we need to determine the number of breaks and their locations a priori in each of the equations in the system. However, this challenging task is converted to a simpler task of determining the number of a few cumulative frequencies when we use a Fourier function. The number of parameters to estimate is reduced significantly, which can lead to a good performance of the tests. We also recommend using a fixed value of cumulative frequencies. We provide the limiting distribution of the Johansen-Fourier tests and the corresponding critical values. Monte Carlo simulations show that the new tests display good size and power properties. An empirical application to the Kilian (2009) dataset shows the result of cointegration, while the conventional Johansen cointegration tests indicate no cointegration. The second essay follows the extensive studies on the similarity and synchronization of member states' economic fundamentals and conditions triggered by the formation of the Economic and monetary union in Europe. Similar institutional and economic conditions are considered essential characteristics, implicit targets, and preferred prerequisite qualifications for the Eurozone members, as the optimal currency area theory indicates. This paper analyzes synchronization in five major macroeconomic variables in the European Union using the dynamic factor model. We do not find significant evidence of synchronization in the Eurozone or EU countries. The degree of synchronization in the Eurozone countries is not greater than that in other countries. Also, we find no significant evidence to show that the EU or Eurozone membership has increased synchronization or similarity within the group over time. Instead, we find that synchronization effects are time-dependent; they are more significant during the financial crisis period. The third and final essay analyzes the co-movements of US housing prices using the state level and metropolitan statistical areas (MSA) data. The objective of the study is to examine the significance and time-varying nature of the co-movements from macroeconomic aspects and determine major factors that drive the movements of the housing prices. Dynamic factor models with time-varying loadings and stochastic volatility (DFM-TV-SV) are employed to estimate the national, regional, and state factors. The results show that the national factor is dominant in explaining the movement of housing prices. On average, the national factor accounts for 79 percent of the variation of housing prices, while its significance is the highest during the housing boom and bust periods in many regions and states. Overall, the significance of each factor varies significantly over time and in different regions. The synchronization effects are also time varying and heterogeneous over different regions and states.
Author: Thomas B. Fomby Publisher: Emerald Group Publishing ISBN: 1784411825 Category : Political Science Languages : en Pages : 772
Book Description
This volume honors Professor Peter C.B. Phillips' many contributions to the field of econometrics. The topics include non-stationary time series, panel models, financial econometrics, predictive tests, IV estimation and inference, difference-in-difference regressions, stochastic dominance techniques, and information matrix testing.
Author: Hyejin Lee
Author: Hyejin Lee
Author: Yan Lu
Author: Hui Liu
Author: Poomthan Rangkakulnuwat
Author: Jason J. Wu
Author: Youngsoo Bae
Author: Patrice Whitely
Author: Suzanne Kathleen McCoskey
Author: Hui-Kuang Yu
Author: Thomas B. Fomby