Primary Fields: Time-series Econometrics, Applied Macroeconomics.
Secondary Fields: Financial Economics, Monetary Economics, Energy Economics.
“Fourier ADL Cointegration Test to Approximate Smooth Breaks with New Evidence from Crude Oil Market” (with V. Arčabić, and H. Lee), Economic Modelling, 2017
- Abstract: Economic data is typically subject to a number of different forms of structural breaks. Ignoring structural breaks in a model can lead to misspecification issues and false conclusions. This paper proposes a new Autoregressive Distributive Lag (ADL) cointegration test in the presence of nonlinear breaks approximated by a Fourier function. The test offers a simple way to capture smooth structural change in time series data. Exact break dates are not required, and the suggested methodology can accommodate unknown number and form of gradual structural change. The testing procedure circumvents the potential power loss which can result from adding more dummy variables in the testing equation. Simulation results show that our procedure has good size and power properties. We demonstrate our test on the empirical example of real oil prices, oil production, and real economic activity, which are subject to structural breaks. The new test suggests that variables are cointegrated, while a conventional ADL test ignores structural breaks and concludes the opposite. This result casts some doubt on conventional oil price models.
“Residual-based Cointegration Tests for Smooth Structural Breaks” (with H. Lee)
- Abstract: It is well documented in the literature that the conventional residual based Engle-Granger (EG) co-integration test assumes common-factor-restriction (CFR). The restriction typically presumes the identical log-run and short-run dynamics in the relationship among the variables. So, a conventional Engle-Granger test poses a serious power loss issue when the CFR doesn’t hold. In real world it is very hard to find one single data which shows the property of CFR. Inducing this fact from the literature, this project develops a new Engle-Granger (EG2) co-integration test that not only prevents the power loss issue from the existing EG test, but also accommodate the underlying nonlinearity in the data through a Fourier transformation. The method is easy to implement and captures the long-run and short-run dynamics of the variables with a pre-determined co-integrating vector. Like the previous project, the time-series data for crude oil price has been used to reaffirm the properties of the newly suggested tests. The new EG (EG2) co-integration test with Fourier approximation detects the co-integration relationship among the crude oil price, crude oil production and real economic activity even when the data shows high cumulative frequencies. On contrary, the conventional EG test with Fourier function fails to detect the co-integration in similar situation due to the restrictive assumption of CFR.
“Global Co-movements of International Reserves and Their Effects” (with J. Lee and H. Isomitdinov)
- Abstract: Recently there has been a growing interest in analyzing the international reserve (IR) holdings data. International reserve holdings prove to be an important safeguard to establish stability of an economy, especially during the periods of economic turmoil. The main purpose of holding IR is to make international payments to repay the debt and hedge against exchange rate risks. A consensus is that international reserve holdings are aimed to smooth out short-run payment imbalances and defuse the possible speculative run on currencies. Due to the increasing trend of global financial integration, it is also important to determine the degree of the effects of outside factors which are exogenous to domestic economic conditions. It is likely that after the financial crisis in 2008 the changed trend of the capital flows in the global world economy can affect the demand for IR holdings. Specifically, this project estimates the global and regional factors in international reserves and evaluate their effects of on the variations of IR holdings in each of the country. Also, international or regional business cycles can affect the demand for IR holdings. That is, these outside factors, which can be comprised of the global common factors of IR holdings, can have important policy implications of both the advanced and emerging countries. This adds another dimension in the literature of IR holding that requires to model the IR holdings.
Work in Progress:
“The Quantile ADL Cointegration Test: A Single Equation Approach” (with J. Lee)
- Abstract: Most of the financial and macroeconomic data are heavy tailed and non-Gaussian. In this situation, the existing cointegration tests potentially fails to capture the cointegration relationship among the variables since they are assuming the median regression and Gaussian error. This paper is trying to develop new quantile co-integration tests in a single equation framework. The new tests statistics would be able to capture the behavior of heavy-tailed, non-Gaussian macro-economic and financial data.
“The Effect of Exchange Rate Regime on Current Account Adjustment: A Factor Model Analysis” (with J. Lee)
- Abstract: Understanding the effect of exchange rate regime on current account adjustment with empirical work is being a common practice in literature. However, economists are with quite different in opinions in analyzing the effect of exchange rate regime on current account adjustment. It is often argued that a more flexible exchange rate system would accelerate the current account convergence. But a series of paper argues that this theory was true during the era of limited financial integration, which could be different from today’s world with potentially more capital flows through out the borders. To resolve this argument this paper addresses the unobserved factors and their cross-correlations associated with both the current account and the exchange rate regime which would systematically answer the question whether the flexible exchange rate regime accelerates the current account convergence across the countries over time and space.