Lecturer

prof.aggr. Luca Grassetti PhD luca.grassetti@uniud.it

Credits

6 CFU

Department

Department of Economics and Statistics

Contents

The course focuses on advanced analysis of fixed-time-interval, discretely sampled data.

Basic elements: typical features of time series (in particular, financial time series); partial and global autocorrelation functions; unit roots and stationarity. A short review of ARIMA modeling will be given.

Non-linear autoregressive models: threshold models TAR, SETAR, LSTAR and Markov Switching models.

Conditional heteroskedatisticity models: ARCH-GARCH models for non-constant variance.

The statistical software R will be used for computer exercises and project analysis.

Pre-requisites

Statistics and econometrics.

Bibliography

Coursebook

-      P.H. FRANSES, D. VAN DIJK, Non-linear time series models in empirical finance, Cambridge University Press, 2000.

-      H. Shumway, D. S. Stoffer, Time Series Analysis and Its Applications: With R Examples (Springer Texts in Statistics), Springer, 2006, second edn.

Other readings:

- H. KANTZ, T. SCHREIBER, Nonlinear Time Series Analysis, Cambridge Univ Press, 2003.

- H. TONG, Non-Linear Time Series: A Dynamical Systems Approach, Oxford Univ. Press, 1990.

- K. CHAN, H. TONG, Chaos: A Statistical Perspective, Springer-Verlag, 2001.

Exam

Written examination and a project.