The Theory That Would Not Die by Sharon Bertsch McGrayne
8 out of 10Bayes Rule [ P(B|A) = P(B) P(A|B) / P(A) ] relates conditional probabilities and is easy to see from a Venn diagram. It has been used to determine probable cause given the observed effects and to assign probabilities to one-time events. It can be used to test hypothesises and can be written in terms of multi-dimensional probability functions [ The posterior distribution of parameters given the data is equal to the prior distribution of parameters times the joint distribution of the data given the parameters divided by the marginal distribution of the data ]. The caveat is that the prior, measuring the uncertainty around the parameter(s), must be determined subjectively.
McGrayne discusses Bayes, Laplace, WWII, optimal search strategies, business decisions, medical research, linguistics, ecology, Bayesians vs. Frequentists, Markov chain Monte Carlo integration, neurology and more!