Labs in STA440 are not graded and they do not count for credit or points. With that said, please do submit your code/attempt to Gradescope at some point before next week’s class - I’ll provide some brief comments.
You may submit this assignment either individually or with your team.
The dataset bikecrash_agg.csv in the GitHub repository contains data from the North Carolina Department of Transportation. Each year, about 1,000 bicyclists are involved in police-reported crashes with motor vehicles in North Carolina, with 60 serious injuries and 20 deaths. This is a tragic yet preventable public health issue. Today’s dataset contains all police-reported bicycle crashes involving a motor vehicle in North Carolina from 2007 through 2014, aggregated at a county level, and also contains characteristics of each of these counties.
The following variables will be used:
crashes: number of crashes in the countypop: the county populationtraffic_vol: mean traffic volume per meter of major roadwayspct_rural: percentage of county population living in rural areaFor this lab, you must use a Bayesian regression approach (choose your favorite!)
Denote counties with over 60 crashes per 100,000 residents per year to be “high-crash” counties. Is there evidence of an association between rurality and being a high-crash county, after adjusting for population? Explain, and quantify any variability in your estimates. Be sure to evaluate model convergence.
Some general considerations:
For more info regarding the data, contact Libby Thomas at the UNC Highway Safety Research Center at thomas@hsrc.unc.edu or John Vine-Hodge at the NCDOT Division of Bicycle and Pedestrian Transportation at javinehodge@ncdot.gov.