Wisdom of Crowds Effect

Psychologists have historically conceived of crowds as suppressing individuality. Recently, an alternative vision of crowds has emerged: Each person potentially brings unique insights, which if combined properly can make the crowd a better decision maker than most individuals. This entry will [Page 777]discuss the conditions under which crowds are wise, whether individuals acting alone can mimic the effects of a crowd, as well as psychological biases that may prevent people from taking full advantage of what crowds have to offer.

Published demonstrations of the wisdom of crowds effect go back to the early 20th century. In one early study from the 1920s, students estimated the temperature in a classroom. When the estimates were averaged together, the resulting group answer was more accurate than the estimate of a typical member. Although early authors attributed the result to some mysterious group property, the statistical underpinning of the effect is now generally understood: A large sample of imperfect estimates tends to cancel out extreme errors and converge on the truth. Subsequent research demonstrated that simple algorithms that weight people equally, such as averaging, often compare favorably to more sophisticated statistical methods of combination. The literature on aggregation was reviewed by Robert Clemen in a 1989 paper in the International Journal of Forecasting and more recently by J. Scott Armstrong in his 2001 book Principles of Forecasting. The power and simplicity of averaging was also featured in James Surowiecki's 2004 best-selling book The Wisdom of Crowds. The logic of tapping diverse perspectives extends to many tasks, including identifying decision objectives, generating alternatives, and choosing among alternatives.