Week 1 Assignment

Part 1

Read the 2018 Charlottesville Child Welfare study completed by the first year of the Public Interest Data Lab class. As you read, think about the following questions:

• Based on your understanding of the child welfare system as we discussed today - which findings stand out the most to you?
• The data we’re working with this semester is pretty similar to the data from the first year of the class with a few key additions. Where do you see opportunities to extend the prior research and dig deeper? What questions appear to have been answered exhaustively with the existing data?

Part 2

Open the week1-example.R file and the bestpractices.R file in R Studio. Mount the data in Veracrypt and read in the data.

You can find your variable assignments here. Multiple people in the class are assigned to each variable but no two people have the same set. Feel free to collaborate with other students in the course!

Everyone has been assigned multiple descriptor variables and outcome variables. Client ID, race, and gender are not assigned - everyone should use them in addition to their assigned variables to break out your data by relevant demographics.

Challenge: If you are already an R allstar, pick a finding from the 2018 report and try to replicate the table/graph/model with the 2020 data. Code from the 2018 report is available on the course Github in the 2018 repo.

What to submit:

• A short writeup (bulleted list, paragraph, etc.) of reflections, comments, or future directions after reading the 2018 report - include a few research questions sparked by reading the report.
• An R script with your exploratory analysis code with your assigned variables - come prepared to chat about what you found!

Send these to the assignments channel on Slack by noon on Monday, February 24.