WSJ column "The Numbers Guys"

I enjoy reading WSJ column "The Numbers Guys" a lot. The column examines numbers and statistics in the news, business, politics and health. Some numbers are flat-out wrong, misleading or biased. Others are valid and useful, helping us to make informed decisions.

The column is wrote by Carl Bialik, a former technology reporter for the Online Journal, is a freelance writer living in Brooklyn, N.Y. He has long had an interest in looking at the way numbers are used, and abused, in the news, business and politics. Carl has a degree in mathematics and physics from Yale University.

He published his reading list in WSJ a month ago, I think it is worth to take a look.

Think3 (7-sep-05)

------------------------------------------------------

Carl's Reading List

August 19, 2005 6:56 a.m.

I have enjoyed reading several books recently on the use and misuse of numbers. Joel Best, a University of Delaware sociology professor, has written two books exposing the subtle choices people make when creating statistics, and the big effects these choices can have. Dr. Best followed up "Damned Lies and Statistics" with "More Damned Lies and Statistics." (The titles play off a famous quote attributed to 19th century British prime minister Benjamin Disraeli: "There are three kinds of lies: lies, damned lies, and statistics.")

In "Tainted Truth," Wall Street Journal reporter Cynthia Crossen exposes the interest groups behind sponsored market research, advertising and, more troublingly, academic and scientific studies.

"Innumeracy," by Temple University math professor John Allen Paulos, explains why his title subject -- the equivalent of illiteracy for numbers -- is widespread and dangerous for society. He followed that book with "A Mathematician Reads the Newspaper," a quirky tour of a standard broadsheet that mixes critiques of numerical misuse with other musings.

Jonathan Koomey distills a career's worth of experience as an energy scientist into "Turning Numbers Into Knowledge." Part III is most germane to this column, with tips on assessing others' numbers and graphs -- plus a gem of a two-page chapter reminding readers that "numbers aren't everything."

The Statistical Assessment Service, a non-profit watchdog group, takes a very modern approach. Articles and shorter posts at Stats.org pick apart misuse of numbers by the media, researchers and industry groups.

And the classic in the genre, Darrell Huff's "How to Lie With Statistics," just turned 50 but is still very relevant. Plus, it's a fun read.