Aleatoriedade, onde esta' voce?

De um post de Peter Norvig:

It is interesting to consider why people are so prone to see patterns in the data, like the cancer clusters around cell phone masts. It turns out that people and other mammals are sensitive to patterns, and are quick to spot them where they exist, and even when they don't exist. On the other hand, people are poor at identifying randomness. Consider the following three plots. In one of the plots each of the blue points is sampled with equal probability from the entire square. Which one is it?

Most people say the rightmost plot (isto e', o ultimo plot) is "most random". Those with some statistical sophistication suspect it may be too random, and pick the middle plot. In fact, it is the leftmost plot (isto e', o priemiro plot) that is a uniform random sample of 250 points on the unit square. In the middle plot, the grid is divided into the 25 squares shown by the light lines, and ten points are placed (with a random uniform distribution) in each of the 25 squares. The plot on the right is formed in a similar way, except it is composed of 64 smaller squares (not shown by lines), each of which has 4 points placed at random. People don't like the leftmost plot because it has several clumps of points that seem non-random. In fact, true randomness consists of a mixture of clumps and non-clumps. Randomness is different from homogeneity.