Key Concepts Learned
- An overview of Git + GitHub
- Quarto basics
- An overview of R
- tidyverse and dplyr
Coding Techniques
- Why we use tidyverse (tibbles vs dataframes)
- A review of basic data manipulation using dplyr in R (select, filter, mutate, summarize, groupby)
- Quarto and how to generate good looking reports using markdown
Questions & Challenges
- No major challenges this week.
Connections to Policy
- Prof. Delmelle mentioned how the course, as opposed to the statistical analysis class, is focused on prediction.
- In addition, public sector data science has very different goals than the private sector. Tradeoffs exist, and we’re not trying to simply optimize profit.
Reflection
- I hadn’t used Quarto so it was cool to see how the code could be deployed using GitHub Pages.