TMA4285 Time Series Models Fall 2011
Course description is given here
Welcome to the course TMA4285 Time Series Models Fall 2011. The first lecture will take place in F2 Tuesday August 23.
Tuesday August 30: Partial autocorrelation and 2.4-2.5.2.
Wednesday August 31: Sample ACF and PACF. Moving average representation. 2.5.2- 2.6
From week 36 on the lecture that is scheduled to be on Thursday 12-14 in F6 will be moved to Wednesday 10-12 in room E404/alias EL23 Electrical Engineering building.
Tuesday September 6: 2.6, 2.7 and 3.1 in the book.
Wednesday September 7: Stationarity of AR(p) processes, Yule-Walker equations
Tuesday September 13: Pacf of Ar(p), Acf, Pacf of MA(q), Dual representation
Wednesday September 14: Dual representation. ARMA(p,q)
Tuesday September 20: Non-stationary processes. Chapter 4.
Wednesday September 21: Transformations and Forecasting
Tuesday Sepember 27: Chapter 5. Forecasting
Wednesday September 28: Forcastfunction, Model Identification
Tuesday October 4. Model Identification, Diagnostic tools.
The fist compulsory exercise is now ready to work on. Deadline for handing in is October 25.
Wednesday October 5. Seasonal Arima Models
Tuesday October 11. Seasonal models and estimation (chapter 7)
Wednesday October 12. No lecture
Tuesday October 18. Chapter 7. Estimation
Wednesday October 19. Chapter 15. Arch and Garch models
A note on uncertainty in the estimators and the information matrix can be found here
Tuesday October 25. Arch and Garch models
Wednesday October 26. State space models
The second compulsory exercise is now ready to work on. Deadline for handing in is November 23.
Tuesday November 1. Kalman filter
Wednesday November 2. Application of the kalman filter.
The score on the first Compulsory exercise is available here
Tuesday November 8. First compulsory exercise. Some topics in time series.
Tuesday November 15. Exam 2010.
Tuesday November 22. Repetition slides from last lecture
The score on the second Compulsory exercise is available here
Tuesdays 14:15-16:00 in F2
Wednesdays: 10:15-12:00 in E404/EL23 Electrical Engineering building.
John Tyssedal tyssedal [at] stat [dot] ntnu [dot] no , Room 1132 SII.
Shahrukh Hussain, Department of Mathematical Sciences, Room 1126 SII. Shahrukh [dot] Hussain [at] math [dot] ntnu [dot] no
Wednesdays 15:15-16:00 in F2. Exercises start in week 35. There will be 10 weekly exercises.
Exercise 1: 2.1 - 2.4 from the book. Solution exercise 1
Exercise 2. Solution Exercise 2
Exercise 3. Solution Exercise 3
Exercise 4. Solution Exercise 4
Exercise 5.Solution Exercise 5
Exercise 6. Solution Exercise 6
Exercise 7. Solution Exercise 7
Exercise 8.Solution Exercise 8
Exercise 9. Solution Exercise 9
Exercise 10. Solution Exercise 10
No exercise in week 43 (October 24.-28.) due to compulsory exercise.
First compulsory exercise
There will be two compulsory exercises. The first compulsory exercise can be found
Some useful R-commands can be found here: Commands
In general you can find out a lot about R by going to the web-site: http://cran.r-project.org/
Second Compulsory Exercise
Wei,William W.S. (2006): Time Series Analysis, "Univariate and Multivariate Methods". Second edition Pearson, Addison Wesley.
Tentative Lecture Plan
|34||1, 2||Stochastic processes and autocorrelation|
|35-36||3||Stationary Time Series Models||1, 2|
|37||4||Nonstationary Time Series Models||3|
|40||6.1-6.2, 6.4||Model Identification, Parameter estimation||6|
|41-42||7.1-7.2.1,7.2.3-7.5||Diagnostic Checking, Model selection||7, 8|
|43||8||Seasonal Time Series||9|
|44||15||Time Series Regression and Garch Models||10|
|45-46||18.1-18.2, 18.5||State Space Models and the Kalman Filter||11,12|
December 1, 2011: 9-13
Meeting hours before exam:
Tuesday 29: 12-14
Wednesday 30: 10-12
As for previous exams you are allowed to bring with you one yellow A5 sheet with your own formulas and notes. The sheet of paper need to be stamped and you can get it at the Department office, seventh floor SII.