|
on Econometric Time Series |
| By: | Westerlund , Joakim (Department of Economics, Lund University); Edgerton, David (Department of Economics, Lund University) |
| Abstract: | This paper develops two very simple tests for the null hypothesis of no cointegration in panel data. The tests are general enough to allow for heteroskedastic and serially correlated errors, unit specific time trends, cross-sectional dependence and an unknown structural break in both the intercept and slope of the cointegrated regression, which may be located different dates for different units. The limiting distributions of the tests are derived, and are found to be normal and free of nuisance parameters under the null. A small simulation study is also conducted to investigate the small-sample properties of the tests. |
| Keywords: | Panel Cointegration; Cointegration Test; Structural Break; Cross-Sectional Dependence; Common Factor |
| JEL: | C12 C32 C33 |
| Date: | 2006–05–04 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:lunewp:2006_013&r=ets |
| By: | Chew Lian Chua (Melbourne Institute of Applied Economic and Social Research, The University of Melbourne); Sandy Suardi (School of Economics, The University of Queensland) |
| Abstract: | This paper tests for the presence of nonlinear dynamics in selected Asian short rates and employs a regime varying unit root test to detect non-stationarity for distinct regimes. Nonlinearities in the form of Markov-switching dynamics are found in all short rates sample. The mean-reverting behaviour of interest rates is dependent on both the level and volatility of interest rates. The occasional random walk and mean-reverting dynamics of short rates are attributed to the macroeconomic fundamentals, exchange rate regimes and monetary policy objectives in these economies. |
| Date: | 2005–09 |
| URL: | http://d.repec.org/n?u=RePEc:iae:iaewps:wp2005n14&r=ets |
| By: | Jörg Polzehl; Vladimir Spokoiny |
| Abstract: | GARCH models are widely used in financial econometrics. However, we show by mean of a simple simulation example that the GARCH approach may lead to a serious model misspecification if the assumption of stationarity is violated. In particular, the well known integrated GARCH effect can be explained by nonstationarity of the time series. We then introduce a more general class of GARCH models with time varying coefficients and present an adaptive procedure which can estimate the GARCH coefficients as a function of time. We also discuss a simpler semiparametric model in which the beta-parameter is fixed. Finally we compare the performance of the parametric, time varying nonparametric and semiparametric GARCH(1,1) models and the locally constant model from Polzehl and Spokoiny (2002) by means of simulated and real data sets using different forecasting criteria. Our results indicate that the simple locally constant model outperforms the other models in almost all cases. The GARCH(1,1) model also demonstrates a relatively good forecasting performance as far as the short term forecasting horizon is considered. However, its application to long term forecasting seems questionable because of possible misspecification of the model parameters. |
| Keywords: | varying coefficient GARCH, adaptive weights |
| JEL: | C14 C22 C53 |
| Date: | 2006–04 |
| URL: | http://d.repec.org/n?u=RePEc:hum:wpaper:sfb649dp2006-033&r=ets |
| By: | Monica Billio (Department of Economics, University Of Venice Cà Foscari); Silvestro Di Sanzo (Departamento de Fundamentos del Analisis Economico, Universidad de Alicante) |
| Abstract: | In this paper we propose a new parametrisation of transition probabilities that allows us to characterize and test Granger-causality in Markov switching models by means of an appropriate specification of the transition matrix. Test for independence are also provided. We illustrate our methodology with an empirical application. In particular, we investigate the causality and interdependence between financial and economic cycles using a bivariate Markov switching model. When applied to U.S. data, we find that financial variables are useful for forecasting the direction of aggregate economic activity, and vice versa. |
| Keywords: | Granger Causality, Markov Chains, Switching Models |
| JEL: | C53 C32 |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:ven:wpaper:20_06&r=ets |
| By: | Rodney W. Strachan (Keele University, Department of Economics) |
| Abstract: | The focus of inference in Bayesian cointegration analysis has recently shifted from the cointegrating vectors to the cointegrating space. Two recent papers - Strachan and Inder (2004) and Villani (2004) - present uniform priors for the cointegrating space using different specifications for identification of the cointegrating vectors. This note clarifies the links between these approaches and shows that while the implied priors on the cointegrating space are identical, the posteriors have very different forms and this difference has implications for the inferences that can be obtained and for computational ease. Central to explaining these results is the specification of the adjustment coefficients under different identifying restrictions. The discussion extends to results on the priors in Geweke (1996) and Kleibergen and Paap (2002) and the interpretation of cointegrating vectors with linear identifying restrictions. |
| Keywords: | Bayesian cointegration; Grassman manifold;Weak exogeneity; Identifying restrictions. |
| JEL: | C11 C32 C52 |
| Date: | 2004–06 |
| URL: | http://d.repec.org/n?u=RePEc:kee:kerpuk:2004/06&r=ets |