B5519 - ANALISI DELLE SERIE STORICHE PER LA FINANZA E LE ASSICURAZIONI

Academic Year 2024/2025

  • Docente: Luca Scrucca
  • Credits: 8
  • SSD: SECS-S/01
  • Language: Italian
  • Moduli: Luca Scrucca (Modulo 1) Gery Andres Diaz Rubio (Modulo 2)
  • Teaching Mode: Traditional lectures (Modulo 1) Traditional lectures (Modulo 2)
  • Campus: Rimini
  • Corso: First cycle degree programme (L) in Statistics, Finance and Insurance (cod. 5901)

Learning outcomes

The course introduces the fundamentals of time series analysis and forecasting with focus on insurance and finance. The first part of the course provides the student with the basic theoretical foundations of modern time series analysis and forecasting. This includes exploratory analyses and tests, trend estimation, non stationarity, cycles and seasonal adjustment. The focus is on linear ARMA processes as a useful paradigm for time series modelling and prediction. The second part of the course is devoted to the analysis of the most common time series from insurance and finance using specialized time series software libraries. This will enable the student to fit time series model and perform forecasting based upon a sound mathematical background. Some extensions to nonlinear models such as those for the conditional variance and regime switching will prepare the student for more advanced courses aimed at specific topics, e.g. risk modelling, financial returns, interest rates, exchange rates, commodities.

Course contents

MODULE 1 - Introduction to time series analysis

  1. Introduction to time series analysis: definitions, descriptive analysis, and graphs.
  2. Introduction to stochastic processes: linear and stationary processes, AR, MA. Autocovariance and Autocorrelation.
  3. Regression models for time series.
  4. Trend-cycle-seasonality decomposition and seasonal adjustment.
  5. ARIMA models.
  6. Time series forecasting and associated uncertainty.
  7. Time series analysis with R.

MODULE 2 - Analysis of financial time series

  1. Features of financial time series.
  2. Analysis of financial returns.
  3. Measuring volatility.
  4. Models for financial time series
    - volatility modelling;
    - ARCH/GARCH models;
  5. Forecasting with ARIMA models.
  6. Forecasting with ARCH/GARCH models.

Readings/Bibliography

MODULE 1

Hyndman R.J., Athanasopoulos G. (2018) Forecasting: Principles and Practice (2nd ed), OTexts: Melbourne, Australia.

MODULE 2

G. M. Gallo, B. Pacini, Metodi quantitativi per i mercati finanziari, Carocci, Roma, 2013 (VII Ristampa).

FURTHER READINGS

  1. Shumway R.H., Stoffer D.S. (2019) Time Series: A Data Analysis Approach Using R, Chapman & Hall/CRC Press, Boca Raton, FL.
  2. Long J.D., Teetor P. (2019) R Cookbook (2nd ed.), O’Reilly Media. https://rc2e.com
  3. Xie Y., Allaire J.J., Grolemund G. (2019) R Markdown: The Definitive Guide, Chapman & Hall/CRC. https://bookdown.org/yihui/rmarkdown
  4. Allaire J.J., Dervieux C. (2024) quarto: R Interface to 'Quarto' Markdown Publishing System. https://quarto.org

Teaching methods

  • Lectures.
  • Classes.
  • Lab sessions with case studies analysed with R.

All students must attend Modules 1 and 2 on Health and Safety online [https://www.unibo.it/en/services-and-opportunities/health-and-assistance/health-and-safety/online-course-on-health-and-safety-in-study-and-internship-areas]

Assessment methods

The exam consists of a written test lasting one and a half hours for each module. The written test must be completed with the assistance of the R software and is structured as follows:

MODULE 1

  • Theoretical questions
  • Time series analysis with R

MODULE 2

  • Theoretical questions
  • Exercises

PARTIAL EXAMS: all students (whether attending or not, and regardless of their enrollment status) may take two partial written tests at the end of each module's lectures.
Students who pass both partial tests with a score of at least 18/30 may choose to accept the final grade calculated as the average of the two partial test scores.

COMPREHENSIVE EXAM: all students (whether attending or not, and regardless of their enrollment status) may take the comprehensive written test covering both modules in a single exam session.

During the written test for Module 1, students are allowed to consult a self-prepared “formula sheet” on a single A4 sheet (double-sided), which may include formulas, comments, examples, R code, etc. No other materials may be consulted.

During the written test for Module 2, consulting any materials is not permitted.

Exam registration is mandatory, and all students must register via the AlmaEsami platform in accordance with the university's general regulations.

Teaching tools

  • Slides of the course
  • Slides on time series analysis with R
  • Exercises
  • Exercises solved with R

Office hours

See the website of Luca Scrucca

See the website of Gery Andres Diaz Rubio

SDGs

Quality education

This teaching activity contributes to the achievement of the Sustainable Development Goals of the UN 2030 Agenda.