My first glance on chapters presented in this book did enough to attract me in the first place. Chapter one is about the catastrophic failure of prediction. Here we are presented with the idea of rating agencies who helped in repackaging the CDOs. As mentioned in the book, it is not about stupidity. End up, these peoples simply do not want the music to stop. One of the very nice quotes in this chapter is: The major difference between a thing that might go wrong and a thing that cannot possibly go wrong is that when a thing that cannot possibly go wrong goes wrong it usually turns out to be impossible to get at or repair. How true... especially when we are dealing with something "out of sample" ...
Chapter two kick off with a very good question: Are you smarter than a television pundit? The author is well-known for his projections in political affair. As such, this chapter capitalize on the author's strength. Chapter 3 is my favorite chapter. It is about winning and losing via baseball game. Those who love "Moneyball" (I love it so much!)will surely love this chapter... One surprise discovery is that the author did consult a Malaysia company while serving for KPMG. Hmm.. the world is really flat! LOL...
Chapter 4 is about weather forecasting and chapter 5 is about earthquake forecasting. Honestly, the said two chapters really blew me away. Ok, I admit that I have zero knowledge in both industries. As such, the evolution of both industries is like an amazing journey to me. After all, both industries are full of numerous uncertainties. Hence, professionals in these industries need to convert such uncertainties into risks. In another words, they are changing something immeasurable into something measurable; even though the measurable does not imply all time accuracy. The best part is... both industries although similar in certain way, the final outcome is very contradict.
By going through weather and earthquake, the author finally turned his attention to economic forecasting in chapter 6. Ok, we all know how bad an economic indicator can be. Well, noises basically do not run far regardless of weather, earthquake or economics. It is the same old stories except it happens ineffectively in a supposed effective capitalism system.
Similar cases happen in chapter 7 when the author presented tons of role models that suppposed to help us in forecasting. Yet, the said models fail once again when noises are obviously much more than the actual facts. In fact, "noises" in the universe are mostly covered from Chapter 1- 7. All 7 chapters provide tons of approximations where some served us well and some failed us completely. Chapter 8 and the remaining chapters deal with methodoloy on how to filter noises and make them better. At least, a little bit at a time, LOL.
Chapter 8 started with an amazing story by Bob Voulgaris where he utilizes facts and try to distant himself from noises. At the end, his forecasting is so much successful. This is follow by the Bayesian Reasoning model (What a model in applied Statistic!!!) and the amazing human brains that defeated programmed chess players (computer). In chapter 10, we have poker games, one of the most important stuff in forecasting. Chapter 11 is another favorite of mine where chartists are being question once again, LOL. The last two chapters focus on the climate of health and the famous terrorist attack.
Finally.... it comes to the end and I must admit that it is very tough to finish a book with more than 500 pages. Fortunately, this is a book with topics that I like. Otherwise, it is very hard to digest some of the "unknown unknown" stuff, LOL. Overall, this is an excellent book to explore especially when we are presented with millions and zillions of noises, thanks to the advancement in information technology these days. However, I think it will be much better if the thickness can be reduce, LOL. Having said that, I am rating this book at 9/10. After some pollution in the last read, thank god that Nate Silver did not disappoint me at all. Thumbs up!
Lastly, listed below are quotes that I personally like it so much:
1. In statistics, the name given to the act of mistaking noise for a signal is overfitting.
2. You are most likely to overfit a model when the data is limited and noisy and when your understanding of the fundamental relationships is poor.
3. Successful gamblers - and successful forecasters of any kind - do not think of the future in terms of no-lose bets, unimpeachable theories, and infinitely precise measurements.
4. This is why our predictions may be more prone to failure in the era of Big Data. Most of the data is just noise, as most of the universe is filled with empty space.
5. Purely statistical approaches toward forecasting are ineffective at best when there is not a sufficient sample of data to work with.
6. If you do detect a pattern, particularly an obvious-seeming one, the odds are that other investors will have found it as well, and the signal will begin to cancel out or even reverse itself.
7. The answer as to why bubbles form, is that it's in everybody's interest to keep markets going up!
8. The winner's curse ~~~ Although of some of the students's bids are too low and some are about right, it's the student who most overestimates the value, who is obligated to pay for them. The worst forecaster takes the "prize".
9. He went to Harvard and has been doing it for 25 years. How can he not be smart enough to beat the market? The answer is: Because there are nine million of him and they all have the same computers that are collocated in the NYSE.
10. Bayes's theorem holds that we will converge toward the better approach. Bayes's theorem predicts that the Bayesians will win.
11. Amateur players, when presented with a chess problem, often frustrated themselves by looking for the perfect move, rendering themselves incapable of making any move at all.
12. Chess masters, by contrast are looking for a "good" move - and certainly if at all possible the best move in a given position - but they are more forecasting how the move might favorably dispose their position than trying to enumerate every possibility.
13. In economic forecasting, the data is very poor and the theory is weak. Hence, the more complex you make the model the worse the forecast gets.
14. The more complex you make the model the worse the forecast gets is equivalent to saying "Never add too much salt to the recipe."
15. The more often you are willing to test your ideas, the sooner you can begin to avoid these problems and learn from your mistakes.
No comments:
Post a Comment