In the current age of ‘big data’ there is an emphasis on effective analysis and insights to aid in policy and business decision making. This book is an good reminder that ‘numbers do not always tell the truth’. They can in fact be used to manipulate and influence popular opinion and outcomes.
Interestingly Bill Gates recommends this 1956 classic book on his 15 books to read list. #6 How to Lie with Statistics, by Darrell Huff.
“I picked this one up after seeing it on a Wall Street Journal list of good books for investors. It was first published in 1954, but it doesn’t feel dated (aside from a few anachronistic examples—it has been a long time since bread cost 5 cents a loaf in the United States).
In fact, I’d say it’s more relevant than ever. One chapter shows you how visuals can be used to exaggerate trends and give distorted comparisons. It’s a timely reminder, given how often infographics show up in your Facebook and Twitter feeds these days. A great introduction to the use of statistics, and a great refresher for anyone who’s already well versed in it.”
Here are 3 things to consider when analysing data or statistics that are used to educate, influence or inform.
• How has the data been collected (opinion polls, surveys, focus groups ) and how have the questions been asked? (open ended, leading, negative/positive etc)
• What is the sample size? Is it representative of the population or group being referenced?
• Who has collected the data and who seeks to benefit from it? (consider context, bias, and source)
An interesting and worthwhile read.