This repository includes a thorough analysis of Federal Sentencing Guidelines. I will use a variety of exploratory and modeling techniques to answer the following questions:
- What are the demographics of individuals sentenced for various crimes (age, race, gender, location, citizenship, level of education, etc.);
- What are the types of sentences handed down (probation vs. prison time vs. fine, etc.);
- How are the sentences handed down relate to the minimum and maximum sentences according to the guidelines (i.e. are sentences closer to the minimum guideline for white defendants and closer to the maximum guideline for defendants of color?)
- How do sentencing practices change after the Booker decision?
- Do prosecutors bring more charges after changes in the mandatory minimums?
- Can we use machine learning to classify edge cases for different Zones and look at those edge cases to see which variables are most influential in pushing someone into one zone vs. another?
The repository is organized as follows:
| Folder | Description |
|---|---|
| Code | This section includes all of the code (both R and Python) used for analysis. |
| Data | This section includes the main datasets used throughout the analyses. |
Data mainly comes from the U.S. Federal Sentencing Commission.
The original blog post can be found here:
Interested in seeing my original code? Go to my GitHub repository here:
https://github.com/jschulberg/Federal-Sentencing
Interested in learning more on the subject? Go to:
https://www.ussc.gov/research/datafiles/commission-datafiles/