Book Review: "The Theory That Would Not Die" (Bayes)

"The Theory That Would Not Die: How Bayes' Rule Cracked the Enigma Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two Centuries of Controversy" by Sharon Bertsch McGrayne, is a book about the history of Bayes rule throughout the life of mathematical sciences. The book looks at how this theory on probability faced dramatic opposition from different parts of the mathematical community over the years, specifically classical frequentest statistics. The book also talks about it's various applications and successes outside of the mathematical community, a clear proponent of the rule surviving throughout history. To be honest, I actually didn't like this book, I was searching for a more in-depth analysis of the various applications of Bayes algorithm and instead got a long history lesson of the mathematicians involved with the theorem over time. The book hardly mentions the actual formula for Bayes, what feels like half the book passes before the author expresses Bayes theorem mathematically. That said, I listened to the book on audible for $23 at 12hrs. I give the book 4/10 stars and only recommend it those searching for the history of Bayes, not learning more about how the algorithm functions mathematically. The following are the chapters of the book:

Part 1: Enlightenment and the Anti-Bayesian Reaction
Chapter 1: Causes in the Air
Chapter 2: The Man Who Did Everything
Chapter 3: Many Doubts, Few Defenders
Part 2: Second World War Era
Chapter 4: Bayes Goes to War
Chapter 5: Dead and Buried Again
Part 3: The Glorious Revival
Chapter 6: Arthur Bailey
Chapter 7: From Tool to Theology
Chapter 8: Jerome Cornfield, Lung Cancer, and Heart Attacks
Chapter 9: There's Always a First Time
Chapter 10: 46,656 Varieties
Part 4: To Prove Its Worth
Chapter 11: Business Decisions
Chapter 12: Who Wrote The Federalist?
Chapter 13: The Cold Warrior
Chapter 14: Three Mile Island
Chapter 15: The Navy Searches
Part 5: Victory
Chapter 16: Eureka!
Chapter 17: Rosetta Stones

Ultimately, I wanted to learn more about Bayes rule as it is critical to areas of math, security, and risk, such as statistics, data analysis, and machine learning. So when I was finished with this book I went on a general Bayes binge, and found several great explanations and in depth explorations of application. My favorite description is probably by the NYTimes in a review of this book:

The theorem itself can be stated simply. Beginning with a provisional hypothesis about the world (there are, of course, no other kinds), we assign to it an initial probability called the prior probability or simply the prior. After actively collecting or happening upon some potentially relevant evidence, we use Bayes’s theorem to recalculate the probability of the hypothesis in light of the new evidence. This revised probability is called the posterior probability or simply the posterior. Specifically Bayes’s theorem states (trumpets sound here) that the posterior probability of a hypothesis is equal to the product of (a) the prior probability of the hypothesis and (b) the conditional probability of the evidence given the hypothesis, divided by (c) the probability of the new evidence.

or even more eloquently stated:

I learned a lot exploring the algorithm along the way, especially when it came to seeing all examples and code out there. I even made a PoC Bayesian classifier for phishing and plan on using similar techniques in my real work. In my searches I also stumbled across ThinkBayes and ended up watching several of the author's lectures as well as digging into the code. In ThinkBayes the author attempts to show readers the many uses of Bayes through preexisting programming knowledge, perfect! I will likely read this book and plan on posting a review, as this looks like the book I was originally looking for. Finally, back to the book at hand, "The Theory That Would Not Die", does include a nice companion page to go along with it. I've added two videos below, one which is a short summary of the book and the other is Sharon's talk at Google.



Sharon's talk at Google was excellent in my opinion: