"For hundreds of years, the Naskapi people of eastern Canada have been using a randomised strategy to help them hunt. Their directionchoosing ceremony involves burning the bones of previously caught caribou and using the random scorch marks which appear to determine the direction for the next hunt. Divesting the decision to an essentially random process circumvents the inevitable repetitiveness of human-made decisions. This reduces both the likelihood of depleting the prey in a particular region of the forest and the probability of the hunted animals learning where humans like to hunt and deliberately avoiding those areas. To mathematicians, using randomness in this way, to avoid predictability, is known as a mixed strategy."(p.129)
"This was Bayes' idea in a nutshell: that he could update his initial belief with new data in order to come up with a new belief. In modern parlance, the prior probability (initial belief) is combined with the likelihood of observing the new data to give the posterior probability (new belief). As much as a mathematical statement, Bayes' theorem was a philosophical viewpoint: that we can never access perfect absolute truth, but the more evidence that accrues, the more tightly our beliefs are refined, eventually converging towards the truth." (157)
"Despite the continued scepticism and its unfashionable nature, there were many distinct successes during the period that Bayes' theorem spent in the hinterland. In the late eighteenth and early nineteenth centuries, artillery officers in the French and Russian armies employed it to help them hit their targets in the face of uncertain environmental conditions.75 Alan Turing used it to help him crack Enigma/6 significantly shortening the Second World War. During the Cold War, the US navy used it to search for a Russian submarine that had gone AWOL77 (an event which inspired the Tom Clancy novel and subsequent film The Hunt for Red October). In the 1950s, scientists used Bayes to help demonstrate the link between smoking and lung cancer.78 The vital premise that all these Bayes adherents had come to accept was that it was OK to begin with a guess, to admit to not being certain of your initial hypothesis. All that was required in return was the practitioner's absolute dedication to updating their beliefs in the face of every piece of new evidence that came along. When applied correctly, Bayes' theorem would allow its users to learn from estimates and to update their beliefs using imperfect, patchy or even missing data. The Bayesian point of view does, however, require its users to accept that they are attempting to quantify measures of belief - to cast off the black and white of absolute certainty, and accept answers in shades of grey. Despite the paradigm shift required - thinking in terms of beliefs rather than absolutes - Bayesian reasoning didn't fit the subjective, anti-science label its detractors had pinned to it. In fact, Bayes absolutely typifies the essence of modern science - the ability to change one's mind in the face of new evidence" (p.159-160)
"We must be wary about overweighting our prior beliefs, too, though. The feeling of confidence in our convictions might make it tempting to ignore small pieces of information that don't change our view of the world significantly. The flip side of allowing ourselves to have prior beliefs as part of the Bayesian perspective is that we must commit to altering our opinion every time a new piece of relevant information appears, no matter how insignificant it seems. If lots of small pieces of evidence were to arrive, each slightly undermining the anthropogenic climate-change hypothesis, then Bayes would allow us to - indeed, dictate that we must - update our view incrementally"(p.167)
Yates also gives wonderful examples from international policy, and the subsequent excerpt could be as handy for Vladimir Putin as it once was for Nixon. You don't want to negotiate with a madman.
"In the context of international diplomacy, sticking to a pure strategy - having a preordained response for any given situation -might reduce the ability of a negotiator to bluff, bluster or manipulate an opponent. Conversely, when negotiating with a despot who is employing a mixed strategy - someone who might, for example, have their finger on the nuclear button one minute, while advocating for total disarmament the next - an opponent might find themselves making more concessions than they would to an actor whose rational actions they find easy to predict. One particular mixed strategy, a form of brinkmanship known in political science as the Madman Theory, was the basis of much of Richard Nixon's foreign policy in the late 1960s and early 1970s. The aim, as the name would suggest, was to convince Nixon's communist opponents that he was more than a little unhinged. He reasoned that if his opponents judged him to be an irrational actor, they would not be able to predict his plays and would thus have to make more concessions to avoid the risk of accidentally triggering him into retaliation". (p.197)
And one other fun example as a last illustration from the book: the strategy of Kleptogamy or the "Sneaky Fucker" strategy.
"Kleptogamy is derived from the Greek words klepto, meaning 'to steal' and gamos, meaning 'marriage' or, more literally, 'fertilisation'. Natural selection suggests that if only the alpha males were reproducing, then the variation in male fitness in future generations would become limited. The evolutionary game theorist John Maynard Smith came up with the theoretical idea of kleptogamy to explain how a wide range of male fitnesses could be sustained over time, although he and his colleagues preferred to call it the 'Sneaky Fucker' strategy. And in some species, the evidence is there to support his hypothesis. A study of the mating habits of grey seals on Sable Island, off the coast of Canada, found that 36 per cent of females guarded by an alpha male were, in fact, fertilised by non-alpha males". (p.189).
















