Gawon Yoon

A Simple Model that Generates Stylized Facts of Returns

This note shows that a very simple model can generate returns that resemble most of the temporal and distributional behavior of long returns surprisingly well. The model is based on the stochastic unit root process introduced in Granger and Swanson (1997).

A note on some properties of STUR processes

This note presents possibly hitherto unnoticed, or only implicitly discussed, properties of the stochastic unit root process developed in Granger and Swanson (1997) and Leybourne, McCabe, and Tremayne (1996).

Are real exchange rates more likely to be stationary during the fixed nominal exchange rate regimes

By testing for the presence of multiple changes in persistence at a priori unknown dates in the real exchange rates spanning more than 100 years over different nominal exchange rate regimes, this note shows that the real exchange rates are more likely to be stationary during the fixed nominal exchange rate regimes than during the floating ones.

Does Purchasing Power Parity Hold Sometimes? Regime Switching in Real Exchange Rates

Standard unit root tests are not very powerful in drawing conclusions regarding the validity of Purchasing Power Parity (PPP). Rather than asking whether PPP holds throughout the whole sample period, we examine, in this study, if PPP holds sometimes by employing Hamilton-type (1989) Markov regime switching models. When at least one of multiple regimes is stationary, PPP holds locally within the regime. There are indeed various reasons that we should expect that the persistence of real exchange rates changes over time. Employing five real exchange rates spanning more than 100 years, we find herein strong evidence that the strength of PPP varies during the sample periods and that there exist stationary regimes in which PPP holds. Throughout the article, we also make comparisons to previous Markov regime switching estimation results by Kanas (2006) on the same data series. The new Markov switching model selection criterion of Smith et al. (2006), which is devised especially for discriminating Markov regime switching models, unambiguously indicates a preference for the Hamilton-type Markov regime switching model employed in this study. We also find that the evidence for PPP is not much different across different nominal exchange rate arrangements.

Nonlinear mean-reversion to purchasing power parity: exponential smooth transition autoregressive models and stochastic unit root processes

Nonlinear exponential smooth transition autoregressive (ESTAR) models are recently very popular in modelling the deviation from purchasing power parity. This article, shows that there is a close relation between the ESTAR models estimated in Taylor et al. (2001) and stochastic unit root (STUR) processes of Granger and Swanson (1997) and McCabe and Tremayne (1995). Also, for a post-Bretton Woods sample period, the real exchange rates from four major countries are tested if they are better described as I(1), ESTAR or STUR processes.

Purchasing power parity and long memory

This article examines the validity of purchasing power parity by estimating long memory parameters with recently suggested exact local Whittle estimators of Shimotsu and Phillips (2005). Little evidence is found for stationarity in the real exchange rates spanning more than 100 years from 16 advanced countries. However, most of the estimates of long memory parameters are less than 1, so that they indicate mean-reversion to parity. Hence, purchasing power parity holds for most real exchange rates studied here.

Nonlinearity in US macroeconomic time series

In this study, we evaluate the linearity of 170 major monthly US macroeconomic time series spanning the years 1959–2002. Employing the linearity test recently proposed by Harvey et al. (2008), which is applicable when the order of integration is uncertain, we determined that more than half of the macroeconomic time series were nonlinear. In particular, approximately 75% of the time series in nominal prices, wages and money category were determined to be nonlinear, whereas the least abundant evidence, corresponding to approximately 43% of the series, was detected in the category of construction, inventories and order.

Does nonlinearity help resolve the Fisher effect puzzle

Even though there is little evidence for linear cointegration, Christopoulos and Léon-Ledesma (2007) recently have found nonlinear cointegrating relations between the US quarterly nominal interest rate and CPI inflation rate. Through Monte Carlo simulations, they also show that the nonlinear relations are responsible for the ‘Fisher effect puzzle’ of less than a proportional coefficient of inflation in the linear Fisher relation. We provide, in this study, an explanation of their simulation results on the Fisher effect puzzle and further examine if nonlinear relations really help resolving the puzzle.

Forecasting with structural change: why is the random walk model so damned difficult to beat?

This paper demonstrates that a naive forecast of no change can produce lower mean square forecast errors than those from true models when structural change exists.

Further analysis of official and black market exchange rates in Brazil: data transformations and structural changes

This paper extends the previous results in Bessler and Yu (1994) on the official and black market exchange rates in Brazil. Rather than taking instantaneous data transformations to produce a stable long-run equilibrium relationship as Bessler and Yu did, the possibility of structural changes in the long-run relationship was considered. It is found that the two approaches have quite different implications on the long-run dynamics of the data series. It is claimed that to fully understand the dynamics of the exchange rate data series, it is necessary to consider the possibility of structural change and explicitly model it.