How to use dice to stop people from lying on surveys

Whenever we turn on the news, we're treated to statistics about things there seem to be no way of verifying. How many people has the average person slept with? How many crimes has the average person committed? The numbers quoted are often the result of surveys. In a survey, there's nothing to keep people honest, especially about things like crimes. Scientists have found that dice can shake the truth out of people.

It's been shown that people lie on surveys. A survey of the number of sexual partners people had — in which participants believed they were hooked up to a lie detector — dramatically shrunk the gap between the numbers of partners usually reported by men and women. One way to keep people from telling a lie is to make them believe that they can't tell anything other than the truth.

Another way to get at the truth is to make people that they sometimes have to tell a lie. A toss of the dice allows people to confess things on surveys that they otherwise wouldn't. When South Africa wanted to conduct a survey about whether or not farmers had killed leopards (an illegal practice), the surveyors brought along a die.

If the farmer tossed the die and got a one, they had to respond "yes" to the surveyor's question. If they got a six, they had to say "no." The rest of the time, they were asked to answer honestly. The die was hidden from the person who was conducting the survey, so they never knew what number the farmer was responding to.

Suddenly, the number of "yes" responses to the leopard question started coming up by more than just one-sixth. This technique — called the randomized response technique — provided a blind that people could use to respond honestly to difficult questions. Depressingly, it was estimated that almost twenty percent of farmers had killed leopards within the last year. The accurate numbers, though, can help the government form more helpful responses, like compensation for livestock lost to leopards, and protect more leopards in the future.

[Proceedings of the Royal Society B via New Scientist]