Picture
(R for Data Science, Wickham & Grolemund)

​Welcome to Data Analysis for the Social Sciences in R!


Learning objectives
​Throughout the course you will...
 
1.     Cultivate a growth mindset in research and develop foundational skills for data analysis. These skills include identifying a research question, creating predictions, interpreting raw data and identifying necessary manipulations, choosing and interpreting relevant formats for visualizing results, and effectively communicating results.

2.     Become literate in applying the R programming language to achieve your exploration goals, including data transformation and meaningful visualization. You will be responsible for a final report, that showcases your research question, your analysis, and a visualization to support a conclusion. You will build up to this report with the assigned tasks in class.
 In this class, we operate as a team. That means respecting one another's opinions,
confusions, insights, interests, identities, and ways of seeing the world.

I design the class with the consistent intention of not overwhelming you. I might fail.
If you need help...
1. Google your question starting with "R" (I'm not being cheeky) - believe it or not, googling questions about code is an acquired skill.
I will help you learn how to create useful google searches to answer your coding questions.
2. In the console, type ? before a function name you want to know more about e.g. "?select", the help information will pop up,
type ?? to find what package the function is in.
3. Post your question to Slack, aka ask your classmates for input
4. Email me at [email protected]
5. Come to my virtual office hours Mondays 12-1pm (sign up)
6. Find a free moment during class
Remember: R is sensitive to detail, var-name ≠ var_name ≠ Var-Name, etc.

Tasks are color-coded as follows: 
​Watch a linked video. Practice skills and concepts. Read a linked text.
Each of these tasks is ungraded (but highly valuable) and to be completed after the day of class under which it's listed.
Many of these tasks are meant to prepare you for the following class's topic.

Weekly quizzes are not graded and will help you refresh concepts from class prep/previous classes. 

Homework will be graded. You will turn in homework via GitHub.
That means you will clone the homework repository locally, then edit, add, commit, and push your changes to the main branch for me to see.

Your final project will be either a team project (undergrad) or a solo project (grad) on a chosen question and dataset.
Using RMarkdown, you'll report your question, a description of the dataset,  and the methods and visualizations you used to explore the question.
Finally, you'll publish this report as a website via GitHub Pages.
​

 Important things to do before out first day of class:
Software setup. <- Set aside time for this.
Read: R for Data Science (R4DS) Chapter 2, Introduction to exploratory data analysis  (very short)

​
3/29 - Week 1 Introductions: Tidy data, the importance of Viz, and GitHub
Tues: Meet R, Rstudio, tidy data, viz, and course overview
In class exercise: checking everyone's set up, open and run emailed viz code
Read: Practice: Exercises in section 4.4 (very short, copy code using "copy" button and paste into a new R script to edit)

Thurs: Meet GitHub
In class exercise: clone your first repo, edit, add, commit, and push changes to the main branch.
Watch: Why viz & A mental model for ggplot2
Practice: R Bootcamp Chapter 1 Sections 1 - 9

4/5 - Week 2 Visualization in ggplot2
Tues: Remeet ggplot2 
In class exercise: meet the geoms (live coding)

Thurs: No class
Individual homework due 4/19:
  • hw1 ggplot2 in GitHub class organization: clone, edit following instructions, add changes, commit and push to main branch
​
4/12 - Week 3 Finding and loading data, collaborating in GitHub
Tues: readr, base R loading, and data types
Read:  Practice:  Work with teammates on team hw 1 - finding your dataset on data.world
Thurs: Collaborating with GitHub
Read:  Practice: Work with teammates on team hw 1 - establishing your questions
Team homework due 4/21:
  • team_hw1 in Github class organization. Find 2 candidate datasets and related research questions


4/19 - Week 4 Data wrangling with dplyr
Tues: select, filter, operators, mutate Thurs: group_by, summarize, and custom functions Individual homework due 5/3:
  • hw2 wrangling in GitHub classroom


4/26 - Week 5 Reporting in Rmarkdown
Tues: titles, formats, parameters
Read:  Thurs: themes, links
Individual homework due 5/10:
  • hw3 in GitHub class organization - Rmarkdown and wrangling cont'd

5/3 - Week 6  Wrangling revisited
Tues: relational data and join functions
Read:  Thurs: custom functions, filter with grepl​ ​Team homework due 5/12:
  • team_hw2 in GitHub class organization​
​
5/10 - Week 7 ​​Storytelling: data viz revisited
Tues: color palettes, legends, custom topics, labels, facets, captions
Read:  Thurs: Guest lecture & Demo, Ronnie Bailey-Steinitz

5/17 - Week 8 Team updates & feedback
Tues: Groups: xgamesmode, poggers, rodeofrogge
Thurs: Groups dogtorphil, curlycoders, zhian21

5/24 - Week 9 Hypothesis testing in R
Tues: What is a significant pattern? Thurs: Common modeling tools

6/1 - Week 10 Group presentations
Tues: dogtorphil, curlycoders, zhian21
Thurs: xgamesmode, poggers, rodeofrogge

Due 6/7: Link to final Rmarkdown report published on GitHub Pages 
​
Grading:
Homeworks 50 pts
  • 4/19: individual hw1 - ggplot2 - 10 pts
  • 5/3: individual hw2 - wrangling - 12 pts
  • 5/10: individual hw3 - Rmarkdown & wrangling revisited- 12 pts
  • 4/21: team hw1 - candidate topics and datasets - 6 pts
  • 5/12: team hw2 - official topic, dataset, data dictionary, additional variables, and transformations - 10 pts
Participation 20 pts (1 pt per class)
Final project 30 pts
  • 20 pts on written Rmd project
  • 10 pts on presentation
  • (5 points of each of the above will be graded by your teammates, i.e. the average of their 1-5 pt evaluations).


Class resources Additional class resources:
Proudly powered by Weebly