Introduction to Time Series
Course Outline for Spring 2012, Statistics 153:
Introduction to Time Series
January 16, 2012
• Instructor: Aditya Guntuboyina (aditya@stat.berkeley.edu)
• Lectures: 12:30 pm to 2 pm on Tuesdays and Thursdays at 160 Dwinelle
Hall.
• Office Hours: 10 am to 11 am on Tuesdays and Thursdays at 423 Evans
Hall.
• GSI: Brianna Heggeseth (bhirst@stat.berkeley.edu)
• GSI Lab Section: 10 am to 12 pm OR 12 pm to 2 pm on Fridays at 334
Evans Hall (The first section will include a short Introduction to R).
• GSI Office Hours: TBA.
All course materials including lecture slides and assignments will be posted on the course site at bSpace.
Short Description: A time series is a set of numerical observations, each one being recorded at a specific time. Such data arise everywhere. This course aims to teach you how to analyze time series data. There exist two approaches to time series analysis: Time Domain approach and Frequency Domain approach.
Approximately, about 60% of the course will be on time domain methods and
40% on frequency domain methods.
Tentative List of Topics: Time Domain Methods: Tackling Trend and
Seasonality, Stationarity and Stationary ARMA models, ARIMA and Seasonal ARIMA models, State space models. Frequency Domain Methods: Periodogram, Spectral Density, Spectral Estimation.
Prerequisite: This course is intended for students who have taken at least one elementary statistics course (e.g., 101) and one elementary probability course
(e.g., 134).
1
Text: The analysis of Time Series (sixth edition) by Chris Chatfield. Some of you might find parts of the text slightly terse and might want a more elaborate book. The following list of books might be helpful:
1. Time Series Analysis with Applications in R by Cryer and Chan. This book has plenty of data analysis examples using R.
2. Fourier Analysis of Time Series by Bloomfield. This book only covers the frequency domain approach.
3. Introduction to Time Series and Forecasting by Brockwell and
Introduction to Time Series
January 16, 2012
• Instructor: Aditya Guntuboyina (aditya@stat.berkeley.edu)
• Lectures: 12:30 pm to 2 pm on Tuesdays and Thursdays at 160 Dwinelle
Hall.
• Office Hours: 10 am to 11 am on Tuesdays and Thursdays at 423 Evans
Hall.
• GSI: Brianna Heggeseth (bhirst@stat.berkeley.edu)
• GSI Lab Section: 10 am to 12 pm OR 12 pm to 2 pm on Fridays at 334
Evans Hall (The first section will include a short Introduction to R).
• GSI Office Hours: TBA.
All course materials including lecture slides and assignments will be posted on the course site at bSpace.
Short Description: A time series is a set of numerical observations, each one being recorded at a specific time. Such data arise everywhere. This course aims to teach you how to analyze time series data. There exist two approaches to time series analysis: Time Domain approach and Frequency Domain approach.
Approximately, about 60% of the course will be on time domain methods and
40% on frequency domain methods.
Tentative List of Topics: Time Domain Methods: Tackling Trend and
Seasonality, Stationarity and Stationary ARMA models, ARIMA and Seasonal ARIMA models, State space models. Frequency Domain Methods: Periodogram, Spectral Density, Spectral Estimation.
Prerequisite: This course is intended for students who have taken at least one elementary statistics course (e.g., 101) and one elementary probability course
(e.g., 134).
1
Text: The analysis of Time Series (sixth edition) by Chris Chatfield. Some of you might find parts of the text slightly terse and might want a more elaborate book. The following list of books might be helpful:
1. Time Series Analysis with Applications in R by Cryer and Chan. This book has plenty of data analysis examples using R.
2. Fourier Analysis of Time Series by Bloomfield. This book only covers the frequency domain approach.
3. Introduction to Time Series and Forecasting by Brockwell and