Statistical Malpractice

By Brian Freedman — November 09, 2007 1 min read
  • Save to favorites
  • Print

On Monday, New York Mayor Michael R. Bloomberg released the results of a complex, A through F grading system for the city’s public schools, 12 percent of which received a D or F. (See: “50 New York Schools Fail Under Rating System,” The New York Times)

Eduwonkette dissects and criticizes the data that the New York City Department of Education, which Eduwonkette said is guilty of “statistical malpractice,” used in compiling the reports.

Eduwonkette highlights what she says are five main flaws: the ignoring of measurement error, arbitrary grade distribution and cutoffs, discrepancies in 6-12 grade schools, poorly constructed comparison groups, and problems with growth models.

Referring to a Bloomberg quote in which he dubbed the reports a “wake-up call” for schools that failed under the new system, Eduwonkette quips:

Through analyzing these data, I’ve concluded that the people in need of a wake-up call work not at F schools, but at the NYC Department of Education.

A version of this news article first appeared in the Blogboard blog.