Sök i programutbudet

Använd sökfunktionen för att leta efter kurser och program i Chalmers utbildningsutbud. Den programplan och utbildningsplan som avser dina studier är i allmänhet från det läsår du började dina studier.

​​​​​​​​​​​​​

Kursplan för

Läsår
TMS086 - Finansiella tidsserier
 
Kursplanen fastställd 2012-02-22 av programansvarig (eller motsvarande)
Ägare: MPENM
7,5 Poäng
Betygskala: TH - Fem, Fyra, Tre, Underkänt
Utbildningsnivå: Avancerad nivå
Huvudområde: Matematik
Institution: 11 - MATEMATISKA VETENSKAPER


Undervisningsspråk: Engelska
Sökbar för utbytesstudenter
Blockschema: X

Modul   Poängfördelning   Tentamensdatum
Lp1 Lp2 Lp3 Lp4 Sommarkurs Ej Lp
0101 Projekt 7,5hp Betygskala: TH   7,5hp    

I program

MPENM ENGINEERING MATHEMATICS AND COMPUTATIONAL SCIENCE, MSC PROGR, Årskurs 1 (valbar)
TKIEK INDUSTRIELL EKONOMI, CIVILINGENJÖR - Finansiell matematik, Årskurs 3 (valbar)

Examinator:

Professor  Holger Rootzén



  Gå till kurshemsida

Behörighet:

För kurser inom Chalmers utbildningsprogram gäller samma behörighetskrav som till de(t) program kursen ingår i.

Kursspecifika förkunskaper

Good knowledge of calculus and linear algebra, knowledge of basic probability and statistics. Some knowledge of stochastic processes is highly desirable.

Syfte

Students will gain an understanding of the classical time-series theory and practice with an emphasis on the modeling of financial time series. They will develop an appreciation of the issues, goals and approaches of this theory through being exposed to basic probabilistic models, tools, and statistical estimation methods specific to this field. In the frame of the general time-series set-up they will develop an appreciation of the specific issues related to the analysis and forecasting of financial returns.

Lärandemål (efter fullgjord kurs ska studenten kunna)

- compute and interpret a sample autocorrelation function
- derive the properties of ARIMA and GARCH models
- choose an appropriate ARIMA/GARCH model for a given set of data and fit the model using an appropriate package
- compute` forecasts for a variety of linear and non-linear methods and models.

Innehåll

This course introduces time-series techniques and their application to the analysis and forecasting of financial time-series. Emphasis is given to nonlinear methods applied to high-frequency financial data. Topics covered include:

Modeling of the marginal distribution of returns
- Modeling the tails (basic Extreme Value Theory)
- Modeling the center

ARIMA models - probabilistic properties and estimation
- Stationary processes
- The autocovariance and the autocorrelation functions
- Basic properties of ARMA processes
- Linear process representation
- Estimation of ARMA processes

ARCH and GARCH processes - theory and practice of volatility modeling
- The ARCH family, definition and relation with ARMA processes
- The tails of Garch processes
- Gaussian quasi-maximum likelihood
- Long memory in volatility, non-stationarities and GARCH
- Multivariate modeling of financial returns.

Organisation

The theoretical discourse is supplemented by hands-on data analysis.
Familiarity with a statistical software analysis tool (like Matlab, Splus, R) is assumed.

Litteratur

Introduction to Time Series and Forecasting, second edition (2002) P.J. Brockwell and R.A. Davis, Springer-Verlag, New York.
The book is supplemented by hand-outs distributed in class.

Examination

Two projects (data analysis), one towards the middle of the period and one at the end (to be done in pairs) together with home assignments (theoretical questions). The home assignments are ABSOLUTELY INDIVIDUAL. No collaboration allowed. Time permitting the course will end with a presentation of the results of the project by each group.


Sidansvarig Publicerad: on 24 jan 2018.