Classroom

Logo

Content for running instances of STAT 545/547M at UBC

View the Project on GitHub STAT545-UBC/Classroom

STAT 545A: Exploratory Data Analysis

This is the course syllabus for the Fall 2018 edition of STAT 545 (click here for the STAT 547M syllabus). You should use this syllabus to:

  1. find information about the course, and
  2. navigate the course.

Quick Navigation

Both STAT 545 and STAT 547M make use of the following tools:

Tool + Link Description
http://stat545.com/Classroom (here) Think of this as the course “home” – and this syllabus as your launch pad to other destinations. Contains lecture notes, assignments, and course information.
assignments, peer review, and participation information Info for Assignments, Peer Review, and Participation assessments can be found here.
Discussion-Internal GitHub repository For internal discussion. The world cannot see this.
Discussion GitHub repository. For public discussion. The world can see this.
STAT545-UBC-students GitHub Organization This will contain one GitHub repository per student, for you to submit homework to and give peer reviews.
UBC canvas This is for grade management. You’ll be interacting with it by submitting a link to your homework.
http://stat545.com This holds course content, such as tutorials. Think of this as a textbook. We’ll point you there when needed. This previously contained the information contained in Classroom, but that eventually became confusing. Some headers there are becoming deprecated.

This framework of tools is under construction, as we move to a solution that’s more scalable in terms of future iterations and multiple collaborators. We appreciate your patience and welcome your feedback!

About STAT 545

STAT 545 is “Part I” of learning how to

Part II is STAT 547M – hope to see you there, too!

Credits: 1.5

Selected Topics

Timing and Location

This course runs from September 4 until October 18, 2018.

We’ll meet as a class every Tuesday and Thursday, 09:30-11:00, in ESB 2012.

I’ll aim to end class at 10:45.

Prerequisites

There are no official pre-requisites for STAT 545A, but most students will have had at least one prior statistics course or comparable experience.

Roots

Jenny Bryan deserves a huge amount of credit for founding and developing both STAT 545 and 547M over many years, along with her TA’s. Some of their content is even being used in this very syllabus. Thank you!

Class Meetings

Here are the topics and links to the notes for each class meeting.

Warning: adjustments are still being made!

Meeting No. Date TA’s Topic Resources
01 sep-04 tues Chad, Sherrie Intro to course and software  
02 sep-06 thurs Chad, Hossam Markdown and GitHub Tutorials for getting started with markdown and GitHub
03 sep-11 tues Rashedul, Sherrie Getting familiar with R & RMarkdown R: stat545: hello r, or adv-r: data structures for a more advanced intro. Rmd: stat545: Rmd test drive.
04 sep-13 thurs Rashedul, Hossam The git workflow; collab with GitHub  
05 sep-18 tues Chad, Sherrie working with data in R; dplyr and the tidyverse  
06 sep-20 thurs Chad, Rashedul ggplot2, Part I  
07 sep-25 tues Hossam, Sherrie ggplot2, Part II  
08 sep-27 thurs Hossam, Rashedul Grouping of tibbles  
09 oct-02 tues Rashedul, Sherrie Tidy data, reshaping  
10 oct-04 thurs Rashedul, Chad, Hossam Guest Lecture: Rashedul, on table joins  
11 oct-09 tues Hossam, Sherrie Advanced R programming; file I/O  
12 oct-11 thurs Hossam, Rashedul The joy of Factors  
13 oct-16 tues Rashedul, Sherrie Revisit ggplot; plotly; practicalities of daily figure-making  
14 oct-18 thurs Rashedul, Chad The model-fitting paradigm in R; broom; deep thoughts about data analytic work  

Expectations:

Evaluation

(Navigation link to Assignments)

To gain marks in this course, you’ll be completing five assignments, and submitting two peer reviews for each assignment. Participation counts too!

NOTE: You must have a GitHub account (free) to earn marks in this course, and then complete the course survey.

Here’s the breakdown of your course grade:

Assessment Weight
5 Assignments 75% (15% per assignment)
10 Peer Reviews 15% (3% per assignment)
Participation 10%

There is no final exam.

Auditing students must still complete and submit all assessments, to be graded on a pass/fail basis.

Assignments and peer review: For information about and links to assignments and peer reviews, go to the assignments page.

Participation: See the participation page.

Teaching Team

Here is your dedicated teaching team!

Teaching Member Position Contact
Vincenzo Coia Instructor Email: vincen.coia@stat.ubc.ca GitHub: @vincenzocoia Twitter: \@VincenzoCoia LinkedIn: vincenzocoia
Chad Fibke Teaching Assistant GitHub: @ChadFibke
Hossameldin Mohammed Teaching Assistant GitHub: @hsmohammed; LinkedIn
Rashedul Islam Teaching Assistant GitHub: @rashedul, LinkedIn
Sherrie Lau Teaching Assistant GitHub: @sherrie9

Please see the “Conversation” section below to determine who to get in touch with for what, and how.

Office hours: Want to talk about the course outside of lecture? Let’s talk during these dedicated times (generally, 11:00-12:00 every Monday, Tuesday, Wednesday). You’re always welcome to schedule alternative times, too.

Teaching Member Date Time Place
Rashedul Tue, Sept 04 11:00 - 12:00 ESB 3174
Vincenzo Wed, Sept 05 11:00 - 12:00 ESB 1043
Sherrie Mon, Sept 10 11:00 - 12:00 ESB 3174
Chad Tue, Sept 11 11:00 - 12:00 ESB 3174
Vincenzo Wed, Sept 12 11:00 - 12:00 ESB 1043
Hossam Mon, Sept 17 11:00 - 12:00 ESB 3174
Rashedul Tue, Sept 18 11:00 - 12:00 ESB 3174
Vincenzo Wed, Sept 19 11:00 - 12:00 ESB 1043
Sherrie Mon, Sept 24 11:00 - 12:00 ESB 3174
Rashedul Tue, Sept 25 11:00 - 12:00 ESB 3174
Vincenzo Wed, Sept 26 11:00 - 12:00 ESB 1043
Chad Mon, Oct 01 11:00 - 12:00 ESB 3174
Hossam Tue, Oct 02 11:00 - 12:00 ESB 3174
Vincenzo Wed, Oct 03 11:00 - 12:00 ESB 1043
Sherrie Mon, Oct 08 11:00 - 12:00 ESB 3174
Chad Tue, Oct 09 11:00 - 12:00 ESB 3174
Vincenzo Wed, Oct 10 11:00 - 12:00 ESB 1043
Chad Mon, Oct 15 11:00 - 12:00 ESB 3174
Hossam Tue, Oct 16 11:00 - 12:00 ESB 3174
Vincenzo Wed, Oct 17 11:00 - 12:00 ESB 1043
Sherrie Mon, Oct 22 11:00 - 12:00 ESB 3174
Rashedul Tue, Oct 23 11:00 - 12:00 ESB 3174
Vincenzo Wed, Oct 24 11:00 - 12:00 ESB 1043

Do you need my permission to enroll or audit in this course? Space is limited, but I’m happy to sign the Change of Registration form if there’s still room.

Conversation, and Getting Help

Are you stuck? First, try to get unstuck by yourself by following the advice of stat545.com: help-general.

While you are getting started, we recommend you seek help within the STAT545 community first, before, e.g. posting to external forums. We are more cuddly.

The instructor and TAs stand ready to assist you, but your peers will also be a great source of good questions and answers. For that reason, we encourage you to seek help in ways that are visible to others.

The options are sort of listed in order of preference. But we realize every situation is different and your comfort level with these approaches will change as you learn more.

  1. Want to talk about content/coding issues? Post an Issue in the Discussion (public) repository.
  2. Want to talk about the course? Post an Issue in the Discussion-Internal (private) repository.
  3. Want to talk in person? Come visit us during office hours!
  4. Want to privately contact Vincenzo? Feel free to send me an email.
    • I look forward to receiving your email, though I do encourage you to post in one of the Discussion repositories unless it’s really not appropriate for either platform.

Basic Issue workflow

Some advice on opening an Issue on GitHub:

Typically, this will trigger an email to the person/team you tagged. The title of your issue will be in the subject line, so I repeat, make it specific. Your description will become the body of the email. At the bottom will be a link to the issue on GitHub.

If all goes well, your helper will respond. I almost always do this directly via GitHub, though simply replying to the email basically works. In any case, this back-and-forth will show up as a series of comments on your original issue. It’s like an email dialogue but better:

Once the problem is resolved, the issue can be closed. Note that closed issues remain accessible, in case anyone needs to consult them in the future.

Annotated Resources

Here are the resources we will be referring to throughout the course, along with a brief description of the resource.

Overarching resources:

  1. http://stat545.com
    • As mentioned earlier, this website can be thought of as a textbook for STAT 545/547.
  2. R for Data Science (aka “r4ds”), by Garrett Grolemund and Hadley Wickham.
    • STAT 545/547 closely mirrors the topics of this book, making this book more of a true “textbook” for the course.

Resources for more specific topics:

  1. Happy git with R, by Jenny Bryan and the STAT 545 TA’s
    • Great for marrying git, GitHub, R, and RStudio in your workflow.
  2. Advanced R, by Hadley Wickham
    • If you want to learn more about R as a programming language, this is a very readable and concise way of doing so.
  3. ggplot2 book, by Hadley Wickham
    • Useful for digging deeper into ggplot2.
  4. RMarkdown book, by Yihui Xie et al.
    • Brand new! Looks like a comprehensive resource for everything R Markdown related.