- Taschenbuch: 272 Seiten
- Verlag: Hodder & Stoughton General Division (1. Mai 2008)
- Sprache: Englisch
- ISBN-10: 0719564654
- ISBN-13: 978-0719564659
- Größe und/oder Gewicht: 13,9 x 1,8 x 19,8 cm
- Durchschnittliche Kundenbewertung: 4 Kundenrezensionen
- Amazon Bestseller-Rang: Nr. 254.560 in Fremdsprachige Bücher (Siehe Top 100 in Fremdsprachige Bücher)
Andere Verkäufer auf Amazon
+ GRATIS Lieferung innerhalb Deutschlands
+ EUR 3,00 Versandkosten
Super Crunchers: How Anything Can be Predicted (Englisch) Taschenbuch – 1. Mai 2008
|Neu ab||Gebraucht ab|
Kunden, die diesen Artikel gekauft haben, kauften auch
Es wird kein Kindle Gerät benötigt. Laden Sie eine der kostenlosen Kindle Apps herunter und beginnen Sie, Kindle-Bücher auf Ihrem Smartphone, Tablet und Computer zu lesen.
Geben Sie Ihre Mobiltelefonnummer ein, um die kostenfreie App zu beziehen.
Wenn Sie dieses Produkt verkaufen, möchten Sie über Seller Support Updates vorschlagen?
'Convincing' * Economist * 'Entertaining and enlightening' * Financial Times * Groundbreaking ... Not only is it fun to read. It just may change the way you think' * Stephen D Levitt co-author of Freakonomics *
When would a casino stop a gambler from playing his next hand? How could a company use statistical analysis to blackball you from the job you want? Why should you worry when customer services pay attention to your needs? Beginning with examples of the mathematician who out-predicted wine buffs in determining the best vintages, and the sports scouts who now use statistics rather than intuition to pick winners, Super Crunchers exposes the hidden patterns all around us. No businessperson, academic, student, or consumer (statistically that's everyone) should make another move without getting to grips with thinking-by-numbers -- the new way to be smart, savvy and statistically superior.Alle Produktbeschreibungen
Derzeit tritt ein Problem beim Filtern der Rezensionen auf. Bitte versuchen Sie es später noch einmal.
I find this opposition misleading because as far as most of the models from this book are concerned, 'garbage in ' garbage out' applies. That is to say that these models are made to test hypotheses, therefore it is not exact to oppose intuition to quantitative methods. Thus it is even more inexact to make the point that number crunching is superior to intuition.
Another weak point of the book is that as introductory as it might be only 6 pages out of 220 pages discuss Bayesian methods and they are to be found at the very end of the book.
However, this book provides an excellent discussion on evidence based medicine. Another very interesting part is the one where the authors points out the factors that facilitate number crunching.
In a nutshell, if you know what 'significantly different from zero' and 'everything else being equal' mean, you should be able to find a better use of your time.
Of course, for somebody who has already received training in statistical methods, there is nothing in this book from a scientific and educational point of view. And for those who have a phobia of maths: Don't worry, there is not a single equation to find.
But that somebody would be me. Still, I couldn't put it aside. And I just wish I had read this book earlier. Because if I had, statistics would have become a serious endeavor of mine. If there is a book out there putting in plain text why statistics are important not only to those who try to do serious academic research, it is definitely this one.
Why did I subtract a star? At some point this book becomes kind of redundant. For those willing to skip pages filled with information they already digested not a problem.
But to sum it up: Fun to read, especially as a primer for statistics classes. Nothing that helps you through those classes except for lots of motivation. And you might suddenly understand why _this_ review is showed to you, not any other.
Die hilfreichsten Kundenrezensionen auf Amazon.com
In this groundbreaking new book, “Super Crunchers”, the author, Ian Ayre, believes that the days of making decisions by relying on intuitions are gone. Today’s best and brightest organizations are analyzing massive databases at lightening speed and gaining greater insights into our human behavior. They are the super crunchers. Companies like Google and Amazon have amassed huge data about our behavior. They know our tastes better than we do, they understand our children’s needs, they know all about the shoes and clothes we buy and wear. They even know how much we’ll pay for our flights and whether the fares will go up or down. They are a new breed of decision makers who are now calling the shots.
But how do these companies arrive at such massive information. Obviously, they need a huge amount of data to get comprehensive conclusions, and the data should be as randomized as possible to avoid bias. Interestingly, such data is now available through specialized companies whose business is to collect figures from computer charts, store receipts, company reports and the like, and sell them to researchers. They have data on the size of our shoes, the foods we eat, the medicines we buy, the games we play and even the colors we favor. Once the data is collected, researchers use regression and statistical analysis to evaluate the effect of different variables on a commodity or a behavioral trend, e.g. does music in factories increase productivity? Would a salary raise improve employee loyalty…..? And so on.
Putting This new data-analysis approach to many fields has made remarkable improvements. Consider the effect on the medical field. The rise of data-based decision making has reversed conventional wisdom. For example it showed that beta blockers can actually help cardiac patients and that estrogen therapy does not help aging women. Now there is a diagnostic program called “Isabel” which allows physicians to enter a patient’s symptoms into a computer and receive the most likely diagnosis. It will also tell the doctor the possible drug that caused the symptoms. Soon it will even specify the most likely therapy. No wonder many doctors are getting concerned about the possible loss of their control over diagnoses once considered a most important factor in their profession.
How are we then to look at this groundbreaking approach to decision making? One cannot dispute its speed and efficiency. It is simply remarkable! Business has put it to beneficial use, but mostly to maximize its profits from the unaware consumers. Medicine stands to gain from it technically while also helping the patient financially and health-wise. But buyer be ware! There are no guarantees and consumers have to view it critically on a case-by-case basis in order to evaluate its risks and benefits.
Super Crunching is crucially about the impact of statistical analysis on real-world decisions. Two core techniques for Super Crunching are the regression and randomization.
1. Regression will make your predictions more accurate (Historical approach):
It all starts with the use of regressions, and although this method is a basic statistical test of causal relationship it's still a very powerful tool that I need to re-introduce in my analytical life.
Regressions make predictions and tell you how precise the prediction is. It tries to hone in on the causal impact of a variable on a dependent. It can tell us the weights to place upon various factors and simultaneously tell us how precisely it was able to estimate these weights.
2. Randomization and large sample sizes (Present/Real-Time approach):
Reliance on historical data increases the difficulty in discerning causation. Large randomized tests work because the distribution amongst the sample are increasingly identical. Think A/B testing on steroids that allows you to quickly test different combinations! Boils down to the averages of the "treated and untreated" groups.
Government has embraced randomization as the best way to test what works. Statistical profiling led to smarter targeting of government support
With finite amounts of data, we can only estimate a finite number of causal effects
3. Neural network
Unlike the regression approach, which estimates the weights to apply to a single equation, the neural approach uses a system of equations represented by a series of interconnected switches.
Computers use historical data to train the equation switches to come up with optimal weights. But while the neural technique can yield powerful predictions, it does a poorer job of telling you why it is working or how much confidence it has in its prediction.
Super Crunching requires analysis of the results of repeated decisions. If you can't measure what you're trying to maximize, you're not going to be able to rely on data-driven decisions.
We humans just overestimate our ability to make good decisions and we're skeptical that a formula that necessarily ignores innumerable pieces of information could do a better job than we could.
You won't find anything ground breaking stuff here, but I can assure you that you will find the nuts and bolts of analysis, backed up with stories from the real life.
It is an easy read who also gives you a few pointers as to what other literature to read. I can highly recommend it.
"Rule of Thumb" vs Scientific Method
"Gut Hunch" vs Verifiable Methodology
If you are on the left side of each of these pairs - read this to see why "the other side" can be very helpful.
If you are on the right side of each of these pairs - read this to see why maybe "vs" should at least be "and" - using scientific method and techniques to quantify or revise the best guesses of "the experts" - combining factors that the experts consider in ways that produce repeatable and verifiable results - from baseball to wine and farther afield.
Between this book and the Numerati, I feel really smart and also super sketched out by everyone knowing what I buy.
Probably should stop leaving reviews.