County level homicide rates by race/ethnicity of victim

In my last post, I plotted the overall US county-level homicide rate (all groups combined) by racial/ethnic demographics.  Much of that correlation is being driven by high black-on-black homicide rates throughout the country.

If I plot the rate by the race/ethnicity of the victim this pattern becomes clear and the group-level correlation weaken somewhat (especially asians and whites), but it’s still there…



hom_by_pct_hispanic_grp_by_re hom_by_pct_white_by_re

Since non-hispanic whites are a little hard to see with the combined plots, here are a few with whites split out:

minimum population size >= 10K (r=0.29)
nhw_homicide_rate_by_pct_black_weighted_regressionminimum population size >= 100K (r=0.39)


Some of this may be driven by underlying regional patterns (a question for a follow up post maybe), but there’s a fairly strong correlation and there are good reasons to think there is a causal relationship driving at least some of the observed relationships (also see similar patterns with asians above).

That’s it for now.


One thought on “County level homicide rates by race/ethnicity of victim

  1. […] EDIT: [See also these scatterplots of homicide rates by U.S. county race of victim against fraction of specified race of total population. The fraction of the county which is Black has a strong positive relationship, while the fraction which is White has a weak negative relationship. From: County level homicide rates by race/ethnicity of victim | Random Critical Analysis […]


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s