Wednesday, May 27, 2015

You've got to ask yourself one question

Two questions, actually. The first is "compared to what?" Am I 45% more likely to be murdered in de Blasio's Manhattan than in de Blasio's Brooklyn, or than in Bloomberg's Manhattan, or Duggan's Detroit, or La Guardia's Manhattan, or in the casbah by Colonel al-Mustard with a candlestick?

Murders are way up so far this year in Manhattan, The Post has learned.

Sixteen people were killed around the borough between the first of the year and Sunday. Over the same period last year, the figure was 11. That’s an increase of about 45 percent.

So given that we're comparing de Blasio's second year with his first, you're more likely to be murdered in de Blasio's Manhattan than in ... de Blasio's Manhattan. Your next question should be something like"No, not 'which borough.' Compared to what risk?" That takes a little more work.

"The Post has learned" is a flexible term. It could mean waiting for the "grim stats" to be released (as when the News wrote effectively the same story in March), or it could mean going to the Police Department's part of the city website and clicking on the links for Manhattan North and South. In the latter case, you'll find that the Post indeed did the arithmetic more or less correctly: Through May 17, the year-on-year increase was 28.6% (7 to 9) in North, 50% (4 to 6) in South. You might also note, in passing, the longer-term data  in the reports: 2015 is down 47% against 2010 and nearly 93% against 1993 in Manhattan North, for example. And if you dug into the files and found the Times's end-of-year wrapup, you might even conclude that this mayor was less likely to murder you than any of his predecessors "since at least 1963, when the Police Department began collecting reliable statistics."

Mayoral intent aside, what does any of that have to do with you? Almost nothing. Murder is not normally distributed among occupational categories, for one thing. Here's the News again, from earlier in the year:

NYPD Chief of Detectives Robert Boyce said each of the seven drug-related murders this year involved marijuana dealers being targeted.


That may or may not be an appreciable change from last year (and it doesn't address, say, the likelihood of street sellers of loose cigarettes dying at police hands), but it should suggest that much of the variance in your individual risk of being murdered is down to something other than the mayoral death panel. And given that the time frame before his latest rampage included the city's record murder-free streak, you should be especially cautious about drawing broad conclusions from purposive samples.

Bad things happen to innocent numbers in the news for several reasons. One is the craft norm that it's OK -- even expected -- to be bad with numbers. Another is that news stories are. well, stories: they put information into narrative contexts that make sense. Hence the Post quotes a "police source" as saying, "City Hall better wake up soon"; local radio (did we mention that this story crops up every month or so?) quotes partially named residents to a different end: “Way safer. Remember how Times Square used to be? It’s nothing like it used to be,” Jason said.

And then there's another reason. Some organizations are deliberately dishonest with numbers in the interest of serving ideological ends. It's hard to imagine a copy editor being punished at a Murdoch product for writing a flagrantly baked headline that makes the enemy camp look bad, but you never really know. So the one question you've really got to ask yourself before you lie with statistics is: Do I feel lucky?

Labels: ,

0 Comments:

Post a Comment

<< Home