Reflection 2

I used publicly available datasets

• Massachusetts Schools (ma_df): I focused on the variable score4, which recorded the average 4th grade test scores
  • https://vincentarelbundock.github.io/Rdatasets/csv/AER/MASchools.csv
• California Schools (ca_df): I analyzed the math variable which records the average math test scores
  • https://vincentarelbundock.github.io/Rdatasets/csv/AER/CASchools.csv

Both are quantitative variables with a wide range of values making them decent candidates for a first digit analysis. Using Python, I pulled out the first digit of each test score from both datasets. Then, I counted how frequently each digit (1-9) occurred. For Massachusetts 4th grade scores digits 5, 6, and 7 dominated and very few scores started with a 1, 2, or 9. For California math scores the distribution was more spread out, with 5 and 6 still common, but smaller digits showing up more often compared to Massachusetts.