We said this week that the New York Times had reported "a 25 percent increase" in 2011 in police officer homicides. The Times didn't note that the number had dramatically declined this year, notes the Grits for Breakfast blog. There have been only 31 compared with 59 at this time last year, says the National Law Enforcement Officers Memorial Fund. The blog accuses the Times of playing up the increase because "sensationalistic bad news draws more readers than stories about positive trends."
Limiting the analysis to police homicides ignores most on-the-job police deaths, which much more frequently happen because of accidents, often in traffic. In 2010, 153 officers died on the job nationwide, but the FBI on which the Times based its analysis counted 56 officers "feloniously killed" that year. So when calculating the increase in the Times story, most on-the-job police deaths weren't counted. Special care is warranted when analyzing statistics involving such small numbers. With more than 700,000 sworn officers in the U.S., these small fluctuations are not necessarily statistically significant. Notably absent from the Times story was any analysis by a statistician on whether these short-term data fluctuations are meaningful. Instead, the article is filled with speculation about the reasons for a trend that may or may not exist, says Grits for Breakfast.