Paper detail

Data scraping, ingestation, and modeling: bringing data from cars.com into the intro stats class

New tools have made it much easier for students to develop skills to work with interesting data sets as they begin to extract meaning from data. To fully appreciate the statistical analysis cycle, students benefit from repeated experiences collecting, ingesting, wrangling, analyzing data and communicating results. How can we bring such opportunities into the classroom? We describe a classroom activity, originally developed by Danny Kaplan (Macalester College), in which students can expand upon statistical problem solving by hand-scraping data from cars.com, ingesting these data into R, then carrying out analyses of the relationships between price, mileage, and model year for a selected type of car.