Stat 474 Introduction to Time Series and Forecasting
Department of Statistics and Biostatistics
California State University, East Bay
Fall 2021
| Course Description | Homework | Important Dates | Software |
| Syllabus | Handouts | Links | |
| Blackboard | podcasts | Data | Online Books |
Week 16: Finals week
- I will have my usual office hours MW 2-3pm.
- I will log in to class at noon on Monday and Wednesday and answer questions. Please do not log in at the end of class time, when the last question is answered I will log out.
Week 15:
- Evaluations: Please do respond to the class evaluation. I would like to hear your feedback about the class. Topics, R, etc.
- Homework Solutions: The solutions for Homework 9 and 10 have been posted on Blackboard.
- One Monday we will go over tidyquant a bit more and try parts of the Project for AAPL.
- This week we will Review TSLM, ETS, and ARIMA modeling.
- On Wednesday we will discuss Hierarchical Time Series Models, Facebook's Prophet, and NNAR.
- Final: The final will be take-home. The final will be available on Wednesday.
- Final: The final for the class will be take-home. You can complete it at home individually. I will be available during the scheduled exam time for questions. See the Homework link.
Week 14:
- Homework: Homework 10 has been posted.
- Homework Solutions: The solutions for Homework 7 and 8 have been re-posted on Blackboard.
- This week we will begin to discuss ARIMA modeling. And we will discuss auto-ARIMA.
- Examples of time seris data.
Week 13:
- Homework: Homework 9 has been posted.
- Homework Solutions: The solutions for Homework 5, 7, and 8 have been posted on Blackboard. If you have not submitted your work for these assignments, you can still submit them for partial credit. And if you have already submitted your homework, if you want to submit and updated version of your homework you can do that also.
- This week we will begin to discuss ARIMA modeling.
- From Rob Hyndman's Github he has shared Chapter 9 ARIMA Models
- Examples of time seris data.
Week 12:
- Monday this week we will be going over Homework 7 and we will discuss the code for Homework 8. How to use the hilo() function and how to use the TSLM() and ETS() functions to produce forecasts.
Week 11:
- Homework: Homework 8 has been posted.
- This week we will finish discussing time series regression models and begin to discuss Exponential Smoothing methods.
- From Rob Hyndman's Github he has shared Chapter 8 Regression Models
Week 10:
- Homework: Homework 7 has been posted. Due date will be after Spring Break.
- Project: The Project has been posted. See the Homework link.
- We will begin time series modeling with a review of linear regression and discuss time series linear modeling.
- From Rob Hyndman's Github he has shared Chapter 7 Regression Models
Week 9:
- Reminders: The take-home Midterm was due last Friday. Homework 5 was due last week also. If you have not turned in the Midterm yet please send me an email about where you are.
- Homework: Homework 5 due date has been extended to the end of next week.
- Homework: Homework 7 has been posted.
- We will go over the Quiz on Monday and the Midterm on Wednesday this week.
Week 8:
- Today we will discuss forecasting error and prediction intervals for forecasting models.
- From Rob Hyndman's Github he has shared his slides from a recent class he taught. I really like his slides for Chapter 5. Chapter 5 toolbox.
- Homework: Homework 6 has been posted.
- On Wednesday we will discuss Judgmental forecasts.
- Sharpie King
- Homework Solutions: I have posted the solutions to all of the homework assignments in Blackboard. I have posted updated solutions to the first three assignments.
- Quiz Solution: I have posted the solution to the first quiz in Blackboard.
- Twitter Thread ACF: Allison Horst Github Allison Horst Twitter ACF
Week 7:
- Midterm: The Midterm will be made available on Wednesday that will be due next week.
- Homework: Homework 5 has been posted.
- Today we will go over the Chapter 4 homework related to simple statistics and return to the discussion of forecasting from Chapter 5.
- On Wednesday will go over the Quiz and the Midterm.
- Midterm:
Week 6:
- Quiz: There will be a take-home quiz given on Wednesday that will be due next week.
- Homework: If you have forgotten to turn in a homework for the class, please submit your homework late for consideration. We will go over homework solutions on Wednesday.
- Today we will continue the discussion about Forecasting models. Today we will discuss Residual Diagnostics and Prediction Intervals.
- RNotebook:
- Quiz: Download and unzip the Quiz R Project. Complete the quiz in the R Notebook. Knit the R Notebook to a .pdf or .docx file. Submit the .Rmd file and either the .pdf or .docx file to Blackboard.
Week 5:
- Announcements:
- Homework: Homework 4 has been posted.
- Today we will discuss Time Series Features. In particular the strength of trend F_t and the strength of seasonality F_s.
- RNotebook:
- On Wednesday we will take a look at the first Forecasting models we will be using in the class.
- RNotebook:
Week 4:
- Homework: Homework 3 has been posted.
- Homework: The solution to Homework 1 has been posted in Blackboard.
- Today we will start with questions about Homework 2. We will discuss the Classical Decomposition and Seasonal Adjustment.
- US Census:
- R package:
Week 3:
- Book: fpp3
- Examples of time seris data. What happened to GameStop Corporation's stock price last week. Question: How do we load stock data into R? This is a good question.
- Today we will begin discussing Time Series plots that show seasonality.
- Homework: Homework 2 has been posted.
- Handouts: The link to the class Jamboard has been added to the Handouts.
- R Notebook:
- Spotlight Wikipedia:
- On Wednesday we will discuss Autocorrelation, White Noice, and the Moving Average Model MA(1).
- R Notebook:
Week 2:
- Book: fpp3
- Today we will begin discussing Forecasting and Time Series Analysis. We will begin with some examples and review/introduce the basics of the tidyverse that are useful for working with tsibble and the other tidyverts R packages.
- Examples of time seris data.
- Spotlight book: r4ds
- On Wednesday we will be examining many of the datasets we will be using in the class. Note that most of the datasets contain a number of time series.
- R Notebook:
Week 1:
- Book: fpp3
- Today we will be discussing the syllabus for the class and the material that will be covered.
- Homework: Homework 1 has been posted.
- Spotlight Software:
- Spotlight Blog post: Prime Hints For Running A Data Project In R