Understanding Numbers

When I managed the finances of a political party the BBC’s political editor explained on TV that donations totalling 6 million pounds would run my party for a year. It was patently absurd. (We needed around 30 million pounds a year; 20% is not really close to 100%). Clearly the political editor of the BBC didn’t think understanding political finances was important because it was just numbers. To my mind this couldn’t be more wrong. It is hard to look at budget negotiations, expense scandals, and funding crises without realizing that numbers matter in politics.

In general media reporting of numbers is often a problem. For instance, Leonard Mlodinow makes the point that the imprecision of reports is often misunderstood. People think the headline number is the “truth” rather than the (hopefully) best estimate anyone can make given the information available.

“One recent August the Bureau of Labor Statistics reported that the unemployment rate stood at 4.7 percent. In July the bureau had reported the rate at 4.8 percent. The change prompted headlines like this one in The New York Times: “Jobs and Wages Increased Modestly Last Month”. … if the Bureau of Labour Statistics measures the unemployment rate in August and the repeats its measurement an hour later, by random error alone there is a good chance that the second measurement will differ from the first by at least a tenth of a percentage point. Would the New York Times then run the headline “Jobs and Wages Increased Modestly at 2P.M.”?” (Mlodinow 2009, page 129-130)

My advice: When reading numbers consider how the data is measured. Surveys will have at least some range associated with them. Don’t think of this as bad. It is necessary, otherwise you’d rarely estimate anything. That said we shouldn’t imbue the reported numbers with magical properties. 4.7% and 4.8% probably aren’t meaningfully different. If a political party is at 40% support and moves to 39% support this is almost certainly within a poll’s margin of error so it doesn’t mean much at all. If the numbers in your survey of customer satisfaction fall a tiny amount it really isn’t time to panic. Life is full of things we don’t totally understand, (randomness/error), the challenge is to focus only on meaningful changes, ideally ones we can do something about.

Read: Leonard Mlodinow, The Drunkard’s Walk: How Randomness Rules Our Lives, Vintage Books 2009.