Bayesian Analysis of Main Bivariate GARCH and SV models for PLN/USD and PLN/DEM (1996-2001)

• Autorzy: Jacek Osiewalski , Anna Pajor , Mateusz Pipień
• Języki publikacji: EN

Abstrakty

EN

The aim of the paper is to present and compare posterior inferences (for the main quantities of interest) obtained using different models. Here we take into account our previous results on model comparison and focus only on three leading SV specifications and two representative GARCH structures: the best one, i.e. the t-BEKK(1,1) model, and the parsimonious t-DCC model, based on the one proposed by Engle (2002). As in our previous papers, we use Markov chain Monte Carlo (MCMC) techniques to conduct our Bayesian approach and, for the sake of comparison, the daily growth rates of two exchange rates: PLN/USD and PLN/DEM (6.02.1996-31.12.2001). We show that sequences of estimates of the conditional standard deviations and correlation coefficients can be moderately similar for good SV and reasonable GARCH models, despite huge differences in model fit and incomparability of the conditional covariance matrices (we condition on different variables in GARCH and SV models).(fragment of text)

Słowa kluczowe

EN

Bayesian econometric; Bayesian models; Econometric modeling; GARCH model; Stochastic models

PL

Ekonometria bayesowska; Modele bayesowskie; Modelowanie ekonometryczne; Model GARCH; Modele stochastyczne

• Czasopismo: Dynamic Econometric Models
• Rocznik: 2006
• Tom: 7
• Strony: 25--35

Twórcy

autor

Jacek Osiewalski

• Cracow University of Economics, Poland

autor

Anna Pajor

• Cracow University of Economics, Poland

autor

Mateusz Pipień

• Cracow University of Economics, Poland

Bibliografia

• Bollerslev T. (1990), Modelling the coherence in short-run nominal exchange rates: A multivariate generalised ARCH Model, Review of Economics and Statistics 72, 498-505.
• Engle R. (2002), Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional heteroskedasticity models, Journal of Business and Economic Statistics 20, 339-350.
• Jacquier E., Polson N., Rossi P. (1995), Models and prior distributions for multivariate stochastic volatility, technical report, University of Chicago, Graduate School of Business.
• Newton M. A., Raftery A. E. (1994), Approximate Bayesian inference by the weighted likelihood bootstrap (with discussion), Journal of the Royal Statistical Society B 56, 3-48.
• O'Hagan A. (1994), Bayesian Inference, Edward Arnold, London.
• Osiewalski J., Pajor A., Pipień M. (2006), Bayes factors for bivariate GARCH and SV models, Acta Universitatis Lodziensis - Folia Oeconomica, forthcoming.
• Osiewalski J., Pipień M. (2004), Bayesian comparison of bivariate GARCH processes. The role of the conditional mean specification, in: Welfe, A. (Ed.), New Directions in Macromodelling, Elsevier, Amsterdam, 173-196.
• Osiewalski J., Pipień M. (2005), Bayesian analysis of dynamic conditional correlation using bivariate GARCH models, Acta Universitatis Lodziensis - Folia Oeconomica 192, 213-227.
• Pajor A. (2003), Procesy zmienności stochastycznej SV w bayesowskiej analizie finansowych szeregów czasowych (Stochastic Volatility Processes in Bayesian Analysis of Financial Time Series), doctoral dissertation (in Polish), published by Cracow University of Economics, Kraków.
• Pajor A. (2005a), Bayesian analysis of stochastic volatility model and portfolio allocation, Acta Universitatis Lodziensis - Folia Oeconomica, 192, 229-249.
• Pajor A. (2005b), Bayesian comparison of bivariate SV models for two related time series, Acta Universitatis Lodziensis - Folia Oeconomica 190, 177-196.
• Pajor A. (2006), VECM - TSV Models for Exchange Rates of the Polish Zloty, Acta Universitatis Lodziensis - Folia Oeconomica, forthcoming.
• Tsay R.S. (2002), Analysis of Financial Time Series, Wiley, New York.
• Tse Y.K., Tsui A.K.C. (2002), A multivariate generalized autoregressive conditional heteroskedasticity model with time-varying correlations, Journal of Business and Economic Statistics, 20, 351-362.