87573 - METODI STATISTICI PER I MERCATI FINANZIARI

Learning outcomes

The aim of the course is to introduce the student to the statistical methods for risk evaluation and portfolio management.

In particular, the student is able to

- evaluate the risk - return profile of financial portfolios;

- specify linear models for financial variables;

- control hypotheses and implement tests for linear relations;

- analyze ARCH and GARCH models;

- evaluate extensions to non-linear specifications.

Course contents

The first part of the course covers the main aspects of the statisticial analysis of financial variables: from a single asset to portfolios, efficient frontier, capital market line and security market line.

The second part of the course covers an important spectrum of theoretical and empirical issues related to linear models in finance (market model and capital asset pricing model), from OLS estimation to hypothesis tests and residual analysis.

Particular attention is paid to eteroschedasticity (White test) and autocorrelation (Durbin Watson and Breusch Godfrey tests), to ARCH and GARCH specifications and to extensions to non linear specifications.

Statistical methods are developed within the context of financial models in order to verify and interpret the empirical results.

Applications to the Italian Stock Market are performed by using appropriate software. Excel and Gretl are extensively used.

Readings/Bibliography

M. Verbeek (2008), A guide to modern Econometrics, Wiley.

Teaching methods

Lectures followed by in-class tutorials.

Assessment methods

Oral exam aiming at the evaluation of the following educational targets:

- knowledge of the statistical methods taught during the course;

- ability to use these methods in order to analyze a financial portfolio;

- ability to use these methods in order to interpret the financial markets.

The grade is graduated as follows:
<18 failed
18-24 sufficient
25-29 good
30 e lode excellent

Teaching tools

Notes, problems and solutions, cases study and examples, software open source Gretl on https://virtuale.unibo.it/

Office hours

See the website of Michele Costa