Identify established standards or benchmarks for reporting crime statistics

[derekeder]

from @RoderickJones:

One thing I would recommend is that you try to identify some standards or benchmarks for reporting of crime statistics from a federal agency (e.g., Dept. of Justice, FBI, etc.). The meaning of the data will be enhanced if you are using existing, accepted definitions. In public health, different indicators are calculated with different denominators (could be all births, all adults, all people, etc.) and the “per” can be per 1,000, 10,000 or 100,000. It is always best to use accepted definitions (and optimally, cite them).

[derekeder]

@RoderickJones, @fgregg do you have a document you could share that would give some guidance on the proper denominators for the crime statistics we are using? Currently calculating rates per 100,000 residents.

Namely:

• homicide
• assault
• battery

[fgregg]

When people see rates what they often do is interpret that as risks. When you are talking about the crimes you mention though, this can be misleading since different subgroups have very different risks.

What I would do for homicide is break out the rates for different subgroups. From http://homicides.redeyechicago.com/, you know the age, sex, race, and location of the victim. I would define some subgroups like 'black men between 18-30', and calculate the rate for these subgroups. For many possible subgroups, the rates will be very low and you can collapse them into an 'everybody else' subgroup.

I don't know if you can get the same victim information for assault and battery though.

rate

See this question on this issue here: http://opendata.stackexchange.com/questions/381/how-to-normalize-the-data-when-mapping-crime-reports

On Tue, Oct 29, 2013 at 11:45 AM, Derek Eder notifications@github.comwrote:

@RoderickJones https://github.com/RoderickJones, @fgregghttps://github.com/fgreggdo you have a document you could share that would give some guidance on the proper denominators for the crime statistics we are using? Currently calculating rates per 100,000 residents.

Namely:

• homicide
• assault
• battery

— Reply to this email directly or view it on GitHubhttps://github.com/smartchicago/chicago-atlas/issues/63#issuecomment-27320326 .

773.888.2718 2231 N. Monticello Ave Chicago, IL 60647

[JamyiaClark]

We commonly use 100,000 as the multiplier when calculating mortality rates with the exception of infant mortality. It is standard to use a multiplier based on literature or what is used by a reputable organization such as the CDC to ensure things are standard. Here is a report that you might find helpful pertaining to deaths: http://www.cdc.gov/nchs/data/nvsr/nvsr61/nvsr61_04.pdf

Per Healthy People 2020 (http://www.healthypeople.gov/2020/topicsobjectives2020/objectiveslist.aspx?topicId=24#), physical assault rate is calculated per 1000. I can't find any references right now on battery, so you might would use the same multiplier as assault.

[danxoneil]

So, @JamyiaClark, if I am to read this correctly, your suggestion is to leave the death rates as-is and change both the assault and battery rates to per 1,000. Is that correct? If so, we can make the change and then do a blog post reffing this thread.

[JamyiaClark]

Yes, it should be per 1000 as opposed to 100,000. @alhank what are your thoughts? Also, the Dept. of Justice provides rates per 1000-- See http://www.bjs.gov/content/pub/pdf/cv09.pdf.

[derekeder]

Sounds like rates per 1,000 residents is the way to go. I'll go ahead and implement this change.

[JamyiaClark]

Yes! Thanks

[derekeder]

All crime datasets are now adjusted per 1,000 residents

http://www.chicagohealthatlas.org/place/englewood#crime_aggravated_assault