Nate Silver

[bigbadwolf]

A perceptive expose of Nate Silver's book, The Signal and the Noise.

What is not reasonable, however, is for Silver to claim to understand how the financial crisis was a result of a few inaccurate models, and how medical research need only switch from being frequentist to being Bayesian to become more accurate.

The ratings agencies, which famously put AAA ratings on terrible loans, and spoke among themselves as being willing to rate things that were structured by cows, did not accidentally have bad underlying models. The bankers packaging and selling these deals, which amongst themselves they called sacks of shit, did not blithely believe in their safety because of those ratings.

Rather, the entire industry crucially depended on the false models. Indeed they changed the data to conform with the models, which is to say it was an intentional combination of using flawed models and using irrelevant historical data.

Silver confuses cause and effect. We didn’t have a financial crisis because of a bad model or a few bad models. We had bad models because of a corrupt and criminally fraudulent financial system.

​

 

[alain]

I'm reading Silver's book over Christmas vacation. I liked the guy before he went into politics. I'll post something after I read the book.

 

[mfegrad]

on my list, as well. people have been bringing him up but i haven't been able to comment yet

 

[bigbadwolf]

It's been a recurring trope over the last few years that bad models designed by incompetent and naive quants were the culprit for the implosion of the subprime mortgages specifically and the "recession" (really an enduring depression) generally. I always loathed that disingenuous explanation. As the reviewer points out, the models and data were tailored to what crooked decision-makers at the summit wanted -- not that innumerate decision-makers gullibly went along with what incompetent quants were telling them. Quants are glorified errand boys. If one doesn't give you what you want, sack him and get another more compliant to your (often unspoken) wishes. I concede it wasn't blunt and obvious but it was clear what the boys at the top wanted, what they needed to keep the racket going, and quants by and large played along with it.

 

[Polter]

and how medical research need only switch from being frequentist to being Bayesian to become more accurate

That's a good one :D

The ratings agencies, which famously put AAA ratings on terrible loans, and spoke among themselves as being willing to rate things that were structured by cows, did not accidentally have bad underlying models. The bankers packaging and selling these deals, which amongst themselves they called sacks of shit, did not blithely believe in their safety because of those ratings.

As for this one, I don't think it's fair to put all the rating agencies, or even all the NRSROs, in the same basket -- I specifically mean Egan-Jones, which I think did a better job.