Time series analysis and its applications solutions pdf

Índice Show

Introduction to Time Series
Lectures: Cory 241. Tuesday/Thursday 12:30 - 2:00.
Classroom and Computer Lab Section: Evans 344. Friday 9-11.
Course Outline:
Prerequisites:
Assessment:
Lab/Homework Assignments:
Announcements:
Collaboration:
Academic Dishonesty:

Introduction to Time Series

People

			Office hours
Instructor	Peter Bartlett	bartlett@stat	Evans 399, Tue 11-12, Thu 10-11.
GSI	Joe Neeman	jneeman@stat	Evans 387, Mon 3-4, Wed 5-6.

Lectures: Cory 241. Tuesday/Thursday 12:30 - 2:00.

Classroom and Computer Lab Section: Evans 344. Friday 9-11.

Course Outline:

An introduction to time series analysis in the time domain and frequency domain. Topics will include: Stationarity, autocorrelation functions, autoregressive moving average models, partial autocorrelation functions, forecasting, seasonal ARIMA models, power spectra, discrete Fourier transform, parametric spectral estimation, nonparametric spectral estimation.

Text:

Time Series Analysis and its Applications. With R Examples., by Robert H. Shumway and David S. Stoffer. Springer. 2nd Edition. 2006. web site.

Prerequisites:

101, 134 or consent of instructor.

Assessment:

Lab/Homework Assignments (25%): posted every one to two weeks, and due on Fridays at 9 (at the start of the section). The grade will be the average of all homework grades except the worst.
Midterm Exams (30%): scheduled for October 7 and November 9, at the usual lecture time and place. Midterm 1: pdf Solutions: pdf. Midterm 2: pdf Solutions: pdf.
Project (10%).
Final Exam (35%): scheduled for Friday 12/17/10.

Lab/Homework Assignments:

1: pdf. Solutions: pdf.
2: pdf. Solutions: pdf. (Beware: there's a mistake in 3b. Thanks to Enzo Marcano for pointing this out.)
3: pdf. [Data for Q4: sunspot.dat sunspot2.dat] Solutions: pdf.
4: pdf. [Data: globtemp2.dat unemp.dat] Solutions: pdf, 4.1 R code, 4.2 R code.
5: pdf. Solutions: pdf,
Project: pdf. Proposal due Wednesday, November 3 (by email). Report due Friday, December 3 at 5pm, in Evans 399.

Lectures:

Chapter/section references are to Shumway and Stoffer.

Thu, Aug 26. Overview, Chapter 1 (+2.3). slides: pdf.
Tue, Aug 31. Section 1.5. slides: pdf.
Thu, Sep 2. Section 1.6. slides: pdf.
Tue, Sep 7. Section 1.6 (+A.1,A.2). slides: pdf.
Thu, Sep 9. Section 3.2. slides: pdf.
Tue, Sep 14. Section 3.2, 3.3, 3.4. slides: pdf.
Thu, Sep 16. Section 3.3, 3.4, 3.5. slides: pdf.
Tue, Sep 21. Section 3.4, 3.5. slides: pdf.
Thu, Sep 23. Section 3.4, 3.5. slides: pdf.
Tue, Sep 28. Section 3.5. slides: pdf.
Thu, Sep 30. Section 3.6. slides: pdf.
Tue, Oct 5. Review. [Joe Neeman]
Thu, Oct 7. Midterm Exam 1.
Tue, Oct 12. Section 3.6. slides: pdf.
Thu, Oct 14. Section 3.6-3.9. slides: pdf.
Tue, Oct 19. Section 3.9. slides: pdf.
Thu, Oct 21. Section 4.1-4.3. slides: pdf.
Tue, Oct 26. Section 4.3. slides: pdf.
Thu, Oct 28. Section 4.3, 4.7. slides: pdf. (This book attributes the name `pole' to the shape of the graph of a rational function.)
Tue, Nov 2. Section 4.7, 4.4. slides: pdf.
Thu, Nov 4. Section 4.4. slides: pdf.
Tue, Nov 9. Midterm Exam 2.
Thu, Nov 11. UC Holiday.
Tue, Nov 16. Section 4.4, 4.5. slides: pdf.
Thu, Nov 18. Section 4.5 slides: pdf.
Tue, Nov 23. Section 4.5, 4.8. slides: pdf.
Thu, Nov 25. Thanksgiving holiday.
Tue, Nov 30. Section 1.5, 1.6, 5.6, 4.6, 4.10. slides: pdf.
Thu, Dec 2. Review. slides: pdf.

Announcements:

Thursday, December 2: The final exam will be open book. There will be five questions. You may answer all five if you wish. Your grade will consist of the total from the best four questions.
Here are some review questions from Shumway and Stoffer for the material since the second mid-term: 1.12, 1.13, 4.16, 4.18a, 4.32, 4.33.
Partial solutions (to 1.12-4.18a): pdf
Tuesday, November 16: Homework 5's due date has been extended to 11am on Tuesday, November 23, 2010, in 399 Evans.
Wednesday, November 3: Homework 5 has been posted. It is due at 9am on Friday, November 19, 2010, in 344 Evans.
The second mid-term exam will cover all material up to and including the lecture on Tuesday, November 2. There will be 3 questions. You should answer all questions. Each part of each question will have a percentage written next to it - the percentage of the grade that it constitutes.
Here are some review questions from Shumway and Stoffer for the material since the first mid-term: 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.21, 4.23, 4.24.
Thursday, October 28: Remember that the second mid-term exam will be in class (12:30-2:00) on Tuesday, November 9. Like the first mid-term, it will be an open-book exam: you can bring any material you like. Exam papers will be handed out at 12:40, the exam will go from 12:45 to 1:55.
Thursday, October 21: If you are looking for ideas for the project, there is a large collection of time series here.
Tuesday, October 19: Information about the project has been posted here. A one-paragraph proposal is due on Wednesday, November 3. Please email it to bartlett at stat.
Thursday, September 30: The first mid-term exam will cover all material up to and including today's lecture. Here are some review questions from Shumway and Stoffer: 1.4, 1.5, 1.6, 1.9, 1.15, 1.16a, 2.6, 3.1, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.10, 3.11, 3.23a.
Monday, September 27: Remember that the first mid-term exam will be in class (12:30-2:00) on Thursday, October 7. It will be an open-book exam: you can bring any material you like. Exam papers will be handed out at 12:40, the exam will go from 12:45 to 1:55. There will be 6 questions. You may answer all six if you wish; your grade will consist of the total from the best five questions. Each part will have a percentage written next to it - the percentage of the grade that it constitutes. Please take notice of this. The percentages reflect the relative significance of the relevant material, not how much time it will take to answer the question.
Monday, August 30: Some R resources referred to in the first computer lab:
- The Comprehensive R Archive Network
- Phil Spector's Introduction to R and R tutorial
- Simple examples: Intro, Input, Plots [rinput.zip]
Tuesday, August 24: To sign up for computer accounts, you will need to obtain a form from Joe. At the first lab section, on this Friday, August 27, Joe will have these forms available, and will also present an introduction to R.

Collaboration:

You are encouraged to work in small groups on homework problems; it's an excellent way to learn. However, you must write up the solutions on your own, and you must never read or copy the solutions of other students. Similarly, you may use books or online resources to help solve homework problems, but you must credit all such sources in your writeup and you must never copy material verbatim.

Academic Dishonesty:

Any student found to be cheating risks automatically failing the class and being referred to the Office of Student Conduct. In particular, copying solutions, in whole or in part, from other students in the class or any other source without acknowledgment constitutes cheating.