No difference

The folklore that "crime rises on full-moon nights"

This is one of the most enduring of all moon sayings. The English word lunatic comes from luna, Latin for moon: the full moon was thought to unsettle the mind and stir up violence. Among police officers, paramedics, and nurses, the sense that "full-moon nights are busy" is still passed down on the job. That isn't a superstition to laugh off — it's the lived experience of people who work the front line every night. Which is exactly why it deserves a square look at the data.

How the verdict is computed

• The data is daily counts from two U.S. cities' police open data: Chicago (all crime, since 2001) and New York (NYPD complaint records, since 2006) — incident-level public records
• Crime counts have strong weekday patterns (more on weekend nights) and seasonality (more in summer), so the expected value is the average of the "same weekday × same month," and we compare actual ÷ expected as an index (the same adjustment as the accidents and births topics)
• Reporting practices and population shift the level over the years, but normalizing by "weekday × year" keeps that out of the full-moon vs new-moon comparison
• Using the lunar phase at each city's local noon, we classify full-moon days (within ±24h of the instant) and new-moon days, and compare each group's mean index against normal (1.00)

See the methodology for the verdict thresholds.

Reading the data carefully

• These are reported incident counts, not true incidence; unreported crime is not included
• The page tests one thing: whether recorded counts are visibly higher on calendar full-moon days. The front line's "full-moon nights are busy" may show up in ways a count doesn't capture — the kind of incident, or how hard each one is to handle

What we can't see yet

This result doesn't mean "the moon has nothing to do with it." Here is what the current method can't see:

• Time of day: the folklore is about the full-moon night. Our data is daily, so a rise confined to a few night hours wouldn't show
• Type of incident: if only fights and disturbances rose, they could be hidden inside a total that includes theft and everything else
• The load on the front line: the same count can mean very different nights; how hard each call is never makes it into the record

What we want to check next

• Use incident times to compare night hours only
• Split incidents by type (violence, disturbances, and so on)

Perhaps the experience of people who work the front line holds something we haven't yet turned into numbers. We'd like to find it in the data one day.

Sources

• Chicago Data Portal — Crimes, 2001 to Present
• NYC Open Data — NYPD Complaint Data Historic
• Moon phase instants computed in-house from Jean Meeus, "Astronomical Algorithms" (UTC)