Police Data

One of the simplest things we can do is to simply count up all the police stops in all of the Los Altos data, and count them by race. Here's what you get when you do that with the Los Altos RIPA data:   Total Stops Stops per hundred per year Relative per capita rate Transient population required to equalize stops         White 1843 6.9 1.00 17735 Hispanic/Latino/a 1137 55.9 8.06 10941 Asian 798 7.6 1.10 7679 Middle Eastern or South Asian 587 14.9 2.15 5649 Black/African American 191 87.8 12.68 1838 "Total Stops" is easy, that's just all the stops the police made. Unsurprisingly, most of the people stopped by the police in Los Altos are white -- because most of the people in Los Altos are white. Suppose we try to normalize that by the population of each race in Los Altos. It's not as easy as it might seem to get those numbers, because not everyone has the same divisions of race. I used a combination fo the 2020 US Census data and the World Population Review . So...

Welcome! This new blog is part of my work with Los Altos for Racial Equity  (LARE) to advocate for racial equity in policing. I'm not gonna lie, it's gonna be pretty nerdy. If you are passionate about racial equity in Santa Clara County, but you don't like math, go check out LARE. There's lots of good policy work to do there and you won't have to say "standard deviation." Over here though, I wanted to start working through some of the amazing complexity in analyzing police data. Like most data analysis, 90% of the work is in getting the data cleaned and organized. But that last 10% can be really tricky to get right. I'll be using this space to explore some analyses, and hopefully get a lot of feedback from you about how we can make the analysis better. All of the code I use is intended to be available on github so that you can see what I'm doing and help me catch my mistakes. My goals are twofold: To get accurate, meaningful data analysis that can ...

 Hello, world!