Saturday, May 25, 2013

Our words

Self-supplied shorter David Brooks: New York Times, May 21, 2013, "What our words tell us"
Evidence from crude data sets like these are prone to confirmation bias. People see patterns they already believe in. Maybe I’ve done that here.
Yes, you have. Welcome to Big Data. Also, in English we generally say "evidence...  is", not "evidence... are".

It turns out, a particularly eminent member of the fraternity of bloggers dedicated to exposing the errors of the philosopher David Brooks is Professor Mark Liberman of Penn, editor and chief contributor to the Language Log. I never noticed this before! Perhaps it's because whenever Brooks says something especially egregious about the social and behavioral sciences I'm busy trying to write the column up and have no time to read Language Log.

This week, in any event, Brooks's errors are demanding ones, and I'm particularly fatigued for unrelated reasons and have not been able to write the column up to my satisfaction, so I'm very glad to point to a masterly takedown here. As well as this, by the great Robin Lakoff.
By Jayson Musson from The Art of Obama.

1 comment:

  1. Q. How should one plead, after a surfeit of crap papers using Google ngrams to seek support for the authors' preconceived opinions?

    A. Ngramercy!

    ReplyDelete