Statistics have always had a bad reputation. We suspect that the statistics may be wrong or that people are using them to distort the truth but we need them to describe our complex society. Sadly, most of the time people accept statistics without question. Even carefully compiled and reported statistics cannot be considered proof but only strong evidence.

Sometimes cleverly-worded statistics can imply a different meaning than what was originally studied. People accept these mutated statistics, no matter how implausible, without question. These bad statistics are then repeated and take on lives of their own so it can be difficult to track down the primary source. (Damned Lies and Statistics, Joel Best, p 1-8)

Consider the following example:
It has been often said that half of all marriages end in divorce. Divorce rate is often calculated from the number of divorce papers and marriage licensed filed in one year. The main problem lies in the couples that file for divorce were married in many different years and not just the current one. It is inaccurate to say that 50% of marriages end in divorce because twice as many marriage licenses are filed in a year than divorce papers. No agency keeps track of particular marriages and so there is no way of knowing what percentage ends in divorce. (More Damned Lies and Statistics, Joel Best, p 84-87)

Too few people are comfortable with the basic mathematical principles, and this makes them poor judges of the numbers they encounter. We need to understand the methods used to generate these numbers to begin to think critically about the numbers we encounter. Part of the problem is that most of the public is innumerate. Innumeracy, the mathematical equivalent of illiteracy, is an inability to deal comfortably with the fundamental notions of numbers and proper chance. A common example: a small child is pleased by the gift of a penny while an older child understands that a penny cannot buy much at all. When people have problems appreciating the differences among big numbers, they tend to uncritically accept statistics. Another problem is that bad statistics often originate with good intentions from people who are innumerate themselves.

Some bad statistics are based on guesses or dubious data. These can be used to stir up public outrage or fear, distort our understanding of our world and can lead governments to make poor policy choices. The solution to bad statistics is not to ignore all statistics but to become better judges of the numbers we encounter. (Damned Lies and Statistics, Joel Best, p 1-8)

Questions to Consider When Critiquing a Newspaper Article

Questions to Consider When Critiquing a Journal Article

Bibliography

Battersby, Mark. Is that a fact? Peterborough, Ont.: Broadview Press, 2010.

Best, Joel. Damned lies and statistics : untangling numbers from the media, politicians, and activists. Berkeley: University of California Press, 2001.

Best, Joel. More damned lies and statistics : how numbers confuse public issues. Berkeley: University of California Press, 2004.