Aug

24

Book Review from Bruno Ombreux

August 24, 2007 |

 I just finished reading, How to Lie with Statistics, from Darrell Huff. This is a short book and a very pleasant read with a quaint charm. It was written in the 1950s when everybody was smoking, as attested by numerous illustrations dotting the pages.

It is targeting a mainstream readership, the "average man," as they called him back then, not the scholar at ease with numbers, trained at avoiding bias. It is about spotting the lie whenever someone is presenting statistics to support a sales pitch, be it from Madison Avenue or Capitol Road. This can be extended to Wall Street and whatever thoroughfare is traversing the Cambridge, Berkeley or Stanford thin air academic publication hubs.

This book is best summarized by its last chapter, which provides a checklist for finding lies in statistics:

  1. Who says so?
  2. How does he know?
  3. What's missing?
  4. Did anybody change the subject?
  5. Does it make sense?

Who says so?

If a toothpaste manufacturer is showing numbers about how great his toothpaste is compared to competition, they may not be as reliable as the same numbers from an independent assessor.

How does he know?

This is about how numbers were collected. Sample bias. The author makes an interesting point that I haven't read very often: a poll is subject to three biases. There is the classical population bias; there is also a bias in the poll questions, which are a sample of possible questions about the subject; and there is a bias in the answers, which are but a sample of the possible opinions of the person answering the poll.

What's missing?

Very often it is the denominator. We keep hearing about how huge the US debt is. It is huge in absolute terms. Divide it by GDP, and it is not as frightening in line with other countries.

Did somebody change the subject?

A statistical non sequitur. The price of rice in Africa has been going up; this is a sure sign of inflation in the USA.

Does it make sense?

I read recently that four percent of French males and one percent of French females were switchers.

Steve Ellison adds:

On the topic of books, I recently spent a couple of hours in the investing section of a Borders bookstore trying to get a sense of the dominant memes that might be influencing the "public play", as Bacon put it.

Three themes, each of which I saw in multiple books, were:

  1. Trend following is the path to profits
  2. A disastrous day of reckoning is coming
  3. Commodities are better investments than stocks 

Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search