Time series: Analysis, Modelling and Forecasting

by Prof. Andrew Harvey

 

16 – 17 September. Universidad Carlos III de Madrid, Getafe, Spain

 

 

Level:           Intermediate

Course Length:         2-days

Overview: The course will show how economic and financial time series can be modelled and analysed. The aim is to provide understanding and insight into the methods used, as well as explaining the technical details. However, the lectures will stress the concepts and the implications for applied work, rather than the mathematical details. Statistical modelling will be demonstrated using the STAMP package and participants will be given the opportunity to use the package in class.

 

Topics Include:

Stationary vs. Non Stationary time series

Structural time series models

ARIMA models

State Space models and the Kalman Filter

Unobserved Components and signal extraction

Seasonality, Trends and Cycles

 

 

Who should attend: The course is suitable for graduate students, researchers in universities, and economists and statisticians working in government, industry or the financial sector.

 

Prerequisites: Participants are expected to have taken an introductory course in econometrics or time series analysis. No previous experience with STAMP is required. Work experience with econometrics would be advantageous. 

 

 

Prof. Andrew Harvey: Andrew Harvey is Professor of Econometrics at the University of Cambridge with a Fellowship at Corpus Christi College. He is also a Fellow of the Econometric Society and a Fellow of the British Academy (FBA). Previously he was a Professor of Econometrics at the London School of Economics. His research interests focus on time-series econometrics, macro-econometrics, financial econometrics, state space models, signal extraction, volatility, quantiles and copulas. Professor Harvey is also one of the main developers of STAMP, an OxMetrics module for structural time-series analysis and forecasting.

 

Further information, including registration on will be available from

http://www.timberlake.co.uk and http://www.oxmetrics.net