How to Lie with Statistics by Darrell Huff and Irving Geis is an engaging primer that demystifies the basic principles of statistics and sheds light on how they can be used to present information in both honest and not-so-honest ways. First published in 1954, this slim volume remains relevant today, serving as a wake-up call for those unaccustomed to critically examining the deluge of numbers that inundate us from Wall Street, Madison Avenue, and various other sources.
Huff’s tone is both tolerant and amused, yet no-nonsense. He expects readers to learn something useful and apply it in their daily lives. Here are some key takeaways from How to Lie with Statistics:
- The Secret Language of Statistics: Despite its mathematical foundation, statistics is as much an art as it is a science. It can be employed to sensationalize, inflate, confuse, and oversimplify data.
- Beware of Faulty Cause-and-Effect Reasoning: Statistics often suffer from faulty cause-and-effect reasoning. Even if you can’t pinpoint a source of demonstrable bias, maintain a healthy degree of skepticism about results.
- Dodges and Tricks: Huff explores various dodges commonly used in statistical presentations, including sample studies, tabulation methods, interview techniques, and result derivation from figures.