Contents |
[edit]
Course Code
IAM 526 (9700526)
[edit]
Credit
(3-0) 3
[edit]
Prerequisites
Introductory knowledge of calculus and statistics; basics of finance
[edit]
Content/ Aims
This course is concerned with recent developments in the time series techniques for the analysis of financial markets. It provides a rigorous account of the time series techniques dealing with univariate and multivariate time series models. The techniques will be illustrated by a number of applications.
[edit]
Learning Outcomes
[edit]
Suggested Textbooks
- Introductory Econometrics for Finance, by Chris Brooks, Cambridge University Press; first edition, 2002.
[edit]
Outline
- Introduction: What is econometrics? Is financial econometrics different from ‘economic econometrics’? Data. Returns in financial modeling. Formulating an econometric model. Reading articles in empirical finance.
- Econometric Packages for Modelling Financial Data : Available packages. Choosing a package. WinRATS. EViews
- Regression Analysis (an overview): What is a regression model? Regression vs. correlation. Simple regression. Assumptions underlying the classical linear regression model. Properties of the OLS estimator. Precision and standard errors. Statistical inference. Multiple regression. The constant term. Calculation of parameters. t-ratio. Data mining and true size of the test.
- Further Issues with the Regression Analysis: Goodness of fit statistics. Violations of the assumptions of the classical linear regression model. Multicollinearity. Diagnostic tests: DW and LM tests of residual serial correlation, Ramsey’s test of functional form misspecification, Jarque-Bera test of normality, and simple tests of heteroscedasticity
- Univariate Time Series Modelling and Forecasting: Notation and basic concepts. Moving average processes. Autoregressive processes. Partial Autocorrelation function. ARMA processes. Box-Jenkins approach.
- Multivariate Models: Simultaneous equations bias. Exogeneity. Estimation. Vector autoregression models. Impulse response.
- Modelling Long-run Relationships in Finance: Stationarity and unit root testing. Cointegration. Error correction models.
- Modelling Volatility and Correlation: Non-linearity. Volatility models. Historical volatility. Implied volatility models. EWMA. AR volatility models. ARCH models. Generalised ARCH models (GARCH). Extension of various GARCH models. Stochastic volatility models.
- Simulation Methods: Monte Carlo simulations. Variance reduction techniques. Bootstrapping. Random number generation.
- Conducting Empirical Research in Finance: What is it for? Selecting a topic. Resources. Getting the data. Choice of software. Presentation.
To see the pdf version of the outline please click this link