Review of The Signal and the Noise: Why So Many Predictions Fail – But Some Don’t

Started Reading: May 25, 2013
Finished Reading: October 13, 2013

Given the technical nature of what Nate Silver does, and some of the early mentions of the book, I had higher hopes for the technical portions of the book. As usual for a popular text, I was left wanting a lot more. Again, the lack of any math left a lot to desire. I wish technical writers could get away with even a handful of equations, but wishing just won’t make it so.

The first few chapters were a bit more technical sounding, but eventually devolved into a more journalistic viewpoint of statistics, prediction, and forecasting in general within the areas of economics, political elections, weather forecasting, earthquakes, baseball, poker, chess, and terrorism. I have a feeling he lost a large part of his audience in the first few chapters by discussing the economic meltdown of 2008 first instead of baseball or poker and then getting into politics and economics.

While some of the discussion around each of these bigger topics are all intrinsically interesting and there were a few interesting tidbits I hadn’t heard or read about previously, on the whole it wasn’t really as novel as I had hoped it would be. I think it should be required reading for all politicians however, as I too often get the feeling that none of them think at this level.

There was some reasonably good philosophical discussion of Bayesian statistics versus Fisherian, but it was all too short and could have been fleshed out more significantly. I still prefer David Applebaum’s historical and philosophical discussion of probability in Probability and Information: An Integrated Approach though he surprisingly didn’t mention R.A. Fisher directly himself in his coverage.

It was interesting to run across additional mentions of power laws in the realms of earthquakes and terrorism after reading Melanie Mitchell’s Complexity: A Guided Tour (review here), but I’ll have to find some texts which describe the mathematics in full detail. There was surprisingly large amount of discussion skirting around the topics within complexity without delving into it in any substantive form.

For those with a pre-existing background in science and especially probability theory, I’d recommend skipping this and simply reading Daniel Kahneman’s book Thinking, Fast and Slow. Kahneman’s work is referenced several times and his book seems less intuitive than some of the material Silver presents here.

This is the kind of text which should be required reading in high school civics classes. Perhaps it might motivate more students to be interested in statistics and science related pursuits as these are almost always at the root of most political and policy related questions at the end of the day.

For me, I’d personally give this three stars, but the broader public should view it with at least four stars if not five as there is some truly great stuff here. Unfortunately a lot of it is old hat or retreaded material for me.

    Syndicated to:

Review of The Signal and the Noise: Why So Many Predictions Fail – But Some Don’t was originally published on Chris Aldrich | Boffo Socko

Some Brief Thoughts on Cliodynamics and Big History

As an electrical engineer (in the subfields of information theory and molecular biology), I have to say that I’m very intrigued by the articles (1, 2) that Marc Parry has written for the Chronicle in the past few weeks on the subjects of quantitative history, cliometrics/cliodynamics, or what I might term Big History (following the tradition of David Christian; I was initially turned onto it by a Chronicle article). I have lately coincidentally been reading Steven Pinker’s book “The Better Angels of Our Nature” as well as Daniel Kanheman’s “Thinking, Fast and Slow”. (I’ll also mention that I’m a general fan of the work of Jared Diamond and Matt Ridley who impinge on these topics as well.)

I’m sure that all of these researchers are onto something in terms of trying to better quantify our historical perspectives in using science and applying it to history. I think the process might be likened to the ways in which methods of computed tomography, P.E.T., S.P.E.C.T, et al have been applied to the areas of psychology since the late 70’s to create the field of cognitive neuropsychology which has now grown much more closely to the more concrete areas of neurophysiology within biology, chemistry, and medicine.

I can see both sides of the “controversy” which is mentioned in the articles as well as in the comments in all of the articles, but I have a very visceral gut feeling that they can be ironed out over time. I say this as areas like behavioral economics which have grown out of the psychology work mentioned in Kahneman’s book become more concrete. The data available for application with relation to history will be much more useful as people’s psychological interactions with their surroundings are better understood. People in general are exceptionally poor at extrapolating statistical knowledge of the world around them and putting it into the best use. For example, although one can make an accurate calculation of the time-value of money, most people who know it won’t use it to determine the best way of taking a large lottery payout (either a lump sum or paid out over time), and this doesn’t even take into consideration the phenomenal odds against even playing the lottery in the first place. Kahneman’s system 1 and system 2 structures in conjunction with more historical data and analysis of the two in conjunction may be a far better method than either that of historians’ previous attempts or that of the quantitative method separately. Put into mathematical terms, it’s much more likely the case that human interactions follow a smaller local min-max curve/equation on a limited horizon, but do not necessarily follow the global maxima and minima that are currently being viewed at the larger scales of big history. We’ll need to do a better job of sifting through the data and coming up with a better interpretation of it on the correct historical scales for the problem at hand.

Perhaps, by analogy, we might look at this disconnect between the two camps as the same type of disconnect seen in the areas of Newtonian and quantum physics. They’re both interlinked somehow and do a generally good job of providing accurate viewpoints and predictions of their own sub-areas, but haven’t been put together coherently into one larger catch-all theory encompassing both. Without the encouragement of work in the quantitative areas of history, we’ll certainly be at a great disadvantage.

    Syndicated to:

Some Brief Thoughts on Cliodynamics and Big History was originally published on Chris Aldrich | Boffo Socko

Some Brief Thoughts on Cliodynamics and Big History

As an electrical engineer (in the subfields of information theory and molecular biology), I have to say that I’m very intrigued by the articles (1, 2) that Marc Parry has written for the Chronicle in the past few weeks on the subjects of quantitative history, cliometrics/cliodynamics, or what I might term Big History (following the tradition of David Christian; I was initially turned onto it by a Chronicle article). I have lately coincidentally been reading Steven Pinker’s book “The Better Angels of Our Nature” as well as Daniel Kanheman’s “Thinking, Fast and Slow”. (I’ll also mention that I’m a general fan of the work of Jared Diamond and Matt Ridley who impinge on these topics as well.)

I’m sure that all of these researchers are onto something in terms of trying to better quantify our historical perspectives in using science and applying it to history. I think the process might be likened to the ways in which methods of computed tomography, P.E.T., S.P.E.C.T, et al have been applied to the areas of psychology since the late 70’s to create the field of cognitive neuropsychology which has now grown much more closely to the more concrete areas of neurophysiology within biology, chemistry, and medicine.

I can see both sides of the “controversy” which is mentioned in the articles as well as in the comments in all of the articles, but I have a very visceral gut feeling that they can be ironed out over time. I say this as areas like behavioral economics which have grown out of the psychology work mentioned in Kahneman’s book become more concrete. The data available for application with relation to history will be much more useful as people’s psychological interactions with their surroundings are better understood. People in general are exceptionally poor at extrapolating statistical knowledge of the world around them and putting it into the best use. For example, although one can make an accurate calculation of the time-value of money, most people who know it won’t use it to determine the best way of taking a large lottery payout (either a lump sum or paid out over time), and this doesn’t even take into consideration the phenomenal odds against even playing the lottery in the first place. Kahneman’s system 1 and system 2 structures in conjunction with more historical data and analysis of the two in conjunction may be a far better method than either that of historians’ previous attempts or that of the quantitative method separately. Put into mathematical terms, it’s much more likely the case that human interactions follow a smaller local min-max curve/equation on a limited horizon, but do not necessarily follow the global maxima and minima that are currently being viewed at the larger scales of big history. We’ll need to do a better job of sifting through the data and coming up with a better interpretation of it on the correct historical scales for the problem at hand.

Perhaps, by analogy, we might look at this disconnect between the two camps as the same type of disconnect seen in the areas of Newtonian and quantum physics. They’re both interlinked somehow and do a generally good job of providing accurate viewpoints and predictions of their own sub-areas, but haven’t been put together coherently into one larger catch-all theory encompassing both. Without the encouragement of work in the quantitative areas of history, we’ll certainly be at a great disadvantage.

Book Review: Charles Seife’s “Proofiness: The Dark Arts of Mathematical Deception”

Charles Seife doesn’t prove that mathematics is essential for a democracy, but he certainly shows how the lack of proper use of mathematics can fray heavily at the edges!

Book Cover for Proofiness: The Dark Arts of Mathematical Deception

Proofiness was a great book to have read over a long Fourth of July holiday. Though many people may realize some of the broad general concepts in the book, it’s great to have a better structure for talking about concepts like Potemkin numbers, disestimation, fruit packing, cherry picking, apple polishing, comparing apples to oranges, causuistry, randnumbness, regression to the moon, tragedy of the commons, and moral hazard among others. If you didn’t think mathematics was important to daily life or our democratic society, this book will certainly change your mind.

Seife covers everything from polls, voting, politics, economics, marketing, law, and even health to show how numbers are misused in a modern world that can ill-afford to ignore what is really going on around us.

This is a fantastic book for nearly everyone in the general public, but I’d highly recommend it for high school students while taking civics.

Original review posted on GoodReads.com on 7/9/12.

Reading Progress
  • 07/07/12 marked as:¬†currently reading
  • 07/07/12 23.0%¬†#
  • 07/09/12 52.0%
  • 07/09/12 Finished book

    Syndicated to:

Book Review: Charles Seife’s “Proofiness: The Dark Arts of Mathematical Deception” was originally published on Chris Aldrich | Boffo Socko