Nate Silver confuses cause and effect, ends up defending corruption
mathbabe.org
mathbabe.org
"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."
A= Financial Crisis B= Bad Models C= Fraudulent System.
Nate said "A<-B" Author says "A<-B<-C"
That is not a mix up of cause and effect.
Author's main complaint seems to be that Nate assumes bad models are an accident, and Author claims they were intentional.
Again, not a mixup of cause and effect. At worst it's a naive interpretation of the correct cause.
If this is true, then the author's claim (mix-up of cause and effect) must be correct.
That said, I didn't read the book so I have nothing to say about whether or not Nate Silver actually does this.
The simplest explanation is that she was, in fact, arguing that corruption caused the financial crisis.
The modeling error in question was independence; that is, if you have five mortgages, each with a 5% change of default, then these can be packaged up as an AAA security as follows: you only lose your money if all five default. A bit riskier package is that you lose if 4/5 default. And so on, each with different returns.
If they are independent, the p(default) = 1/20^5. If they are dependent, it is 1/20. Now multiple mortgage pool size by a 100 or 1,000 or 10,000 (?) and see how far off the estimated risk is. :)
Now combine this with a 30-to-1 leverage when buying these "AAA" securities.
(This was quite a good problem to work through with my daughter to see what that little "independence" assumption means. :)
His main point here was that modeling failures are typically due to out-of-sample conditions; when the housing bubble broke, the markets were might more tightly coupled across the country than the modelers assumed. While they could have seen this kind of dependence if they looked to Japan, there was no such precedence in the US in recent history.
My personal belief is that they knew of the flaw of the models but did not care since their personal incentives were more profitable if the model was not fixed.
But the kids in Business School would constantly write him and ask him for new ways to rig the game.
She states:
>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 (see points 64-69 here for more).
So C(corruption) directly leads to B(bad model). She does not argue that A(everything falling apart)<-C anywhere in the piece. Silver is claiming that A<-B. He is not commenting about C. So while Silver's claim may not identify the absolute root cause, the author does not actually prove that his cause and effect analysis is flawed. If anything, she has shown that it may be incomplete.
What, specifically, isn't true?
So C(corruption) directly leads to B(bad model). She does not argue that A(everything falling apart)<-C anywhere in the piece.
The point of the piece is that the financial meltdown stemmed from corruption, not from models. If this wasn't her point, then why else would she have written this piece?
If I choose to shoot you with a gun, and have a variety of appropriate guns, it is not the fault of the specific gun chosen that it was used to kill you. I had motive, opportunity, and alternate means available.
If I smashed your head in with a hammer, would people claim the hammer was the cause of your death? Is "hammer caused death" the end of the story, or even particularly important to the related series of causes and effects?
She's arguing that it's not, that Silver's cause and effect analysis is irrelevant because his purported cause is purely incidental. Intentionally inaccurate models were simply an instrument designed to further the self-interest of individuals.
(And further, she doesn't need to provide a "proof" to make this claim. But she does offer a compelling argument.)
She doesn't appear to be disputing the idea that following bad models caused the crisis — instead, she just seems to be saying Silver missed the fact that the models were deliberately bad rather than simply a poor application of math.
A few quotes from the author herself:
"the entire industry crucially depended on the false models."
"Silver gives four examples what he considers to be failed models at the end of his first chapter, all related to economics and finance. But each example is actually a success (for the insiders) if you look at a slightly larger picture and understand the incentives inside the system."
She's not disputing that the models were false or even that acting in accordance with the models is what caused the crisis. She's disputing that this was accidental.
An argument doesn't have to contain a false statement to have no baring on the discussion.
And more generally it's quite possible for a thing to have multiple causes, and in this universe this is generally true for everything we witness. So if A causes C that doesn't mean that B can't also cause C "by definition". I'm not aware of any serious philosphical framework that says that events must have only a single cause, though many philosophers from Aristotle onwards[1] but great stock in the "final cause" of things, but that would be either "God" or "The Big Bang" depending on your religion or lack thereof and nobody was arguing for those.
And as an aside, the words "by definition" in an argument that isn't on it's surface about definitions is generally a bit of a red flag.[2]
[1]http://en.wikipedia.org/wiki/Teleology [2]http://lesswrong.com/lw/nz/arguing_by_definition/
mathbabe is saying that fixing B is not straightforward, because B<-C, and fixing C is very, very difficult. Bad models exist because people have incentives to make them bad.
She's also saying, I think, that fixing B by itself won't fix A, because B is not the root cause; C is. Fixing B without fixing C just means that C will manifest itself somewhere else, and A will still happen. In other words, there are many causal routes from C to A, and fixing B by itself only blocks one of them. So A<-C is true regardless of the state of B.
Everything falling apart would be hyper-inflation in addition to capital control and gold confiscation : )
That could be 'D'.
Latter or sooner we'll learn if D <- A ; )
This is faulty reasoning. A pool ball may go into a pocket because it was hit by a cue ball. In this case the cue ball hitting the other ball is the cause of the other ball falling into the pocket. Yes, you can look back into the chain of causes to find one further back, e.g., the fact that a person used a pool cue to hit the cue ball into the other ball. This doesn't mean that the first cause you found was not a cause, and certainly doesn't mean that "by definition".
If a corrupt and fraudulent system could have brought about the financial crisis by some means other than causing bad models (which I assume is true), then you can say that the bad models were not a necessary part of the causal chain. But you can't say that they weren't part of the causal chain at all. As a matter of fact (at least according to assumptions everyone is making in this topic's thread) they were.
If the models had been more accurate - for example, if they had more properly reflected the way that the value of a bundle of mortgages will suddenly lose value as housing prices decline - banks would not have been able to pile up such huge risks and high leverage.
You can only justify things like 30X leverage if you believe the securities in question have essentially no risk - because at that leverage, a 3% loss in value means you're wiped out.
Sure you can. The root cause of the crisis was people gaming the system. There are many ways to game the system; faulty models are only one of them.
All routes to that particular method of gaming. There are other methods.
A<-C AND B<-C
implying that B wasn't necessary for A as long as C.
Also, I'll address the accusation that Nate is confusing cause and effect.
Nate's assertion is A<-B If he had confused cause and effect than that corrected form would be B<-A, or, that the financial crisis caused bad models.
So the Author's mistake is that (A<-C AND B<-C) != (B<-A), or, that her attack on Nate is inconsistent with what she believes is the correct logic.
Silver assumes that the systems fail because the models are bad. O'Neil is instead claiming those are just correlations and not a cause and effect relationship. Basically the models are bad and the systems failed because the people providing the data were corrupt. Using your example: "A<-C" and "B<-C"
This seems to be her thesis:
To be crystal clear: my big complaint about Silver is naivete, and to a lesser extent, authority-worship.
Having a domain name that is short and rememberable != linkbait.
Surely none of her audience expect to see pics of babes on mathbabe.com
"Bad Model" in Silver's view is really "bad modelling" -- a problem with the statistical technique (frequentist vs. bayesian) used to model the data.
"Bad Model" in O'Neil's view is really "bad data" -- intentionally skewed numbers as a consequent of conscious or sub-conscious eliding or redactory effects on the data populating the model, for purposes other than accuracy: financial gain, for instance.
O'Neil's point is that even a frequentist model would have been effective had the data not been massaged. On this view O'Neil's view is correct: the cause was not "bad modelling" but "bad data." The "bad data" in the model was an "effect" of corruption, not the root "cause" of the financial meltdown.
So it goes that corruption caused bad data, which caused a bad analysis by the model(she claims that both the data and model are bad), which caused the financial meltdown.
That does not invalidate Silver's point. It merely points out that Silver's analysis may be inadequate.
This post really has nothing to do with techniques or "bad data" or a bayesian vs. frequentist debate.
Her point is that bad modeling was entirely incidental and inconsequential as a cause of the financial meltdown. To repeat an example I used previously, if I smashed your head in with a hammer, Silver would essentially be saying "a hammer caused davesims death."
The statement may be technically true, but it's a shallow analysis of cause and effect. It's unsatisfying because it gives too much significance to an incidental link in the complete chain of events.
I disagree, but maybe I'm missing something. This early quote, regarding 'bayesian vs. frequentist' seems to sum up O'Neil's view of Silver fairly well to me:
"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."
And later on regarding 'bad data,' a point she reiterates several times:
"In other words, it’s not that there are bad statistical approaches which lead to vastly over-reported statistically significant results and published papers (which could just as easily happen if the researchers were employing Bayesian techniques, by the way). It’s that there’s massive incentive to claim statistically significant findings, and not much push-back when that’s done erroneously, so the field never self-examines and improves their methodology. The bad models are a consequence of misaligned incentives."
I do think in the above quote O'Neil is equivocating between the idea of a 'bad model' and the skewed data or overreaching significance applied to the model.
Her fundamental point, which she could have done a better job communicating I think, is that it wasn't the models themselves that were bad, bayesian or otherwise, but the data in the models and at times the inordinate significance applied to those models that was the real cause of the meltdown.
[0] http://en.wikipedia.org/wiki/Proximate_and_ultimate_causatio...
- The ratings agencies...did not accidentally have bad underlying models.
He first talks about how the models were defective, and then goes on at length to describe the perverse incentives for developing and keeping these models, and holds the responsible parties to the fire for willful ignorance and unabated greed. He could have made some of these points more strongly, but I don't think that he skirted over the real issues.
- the only goal of a modeler is to produce an accurate model.
Actually he speaks quite a bit about the reasons that various forecasters generate models in the first place, and their motivations and responsibilities. For example, the Weather Channel's skewed "wet" forecasts. They will, for example, predict a 20% chance of rain if their models show only a 5% chance. On the one hand it is a bit dishonest, but on the other hand there is a net utility in doing so. Part of the problem is that the general public doesn't understand what the percentages really signify, so it may be of some benefit to emphasize that it really could rain, it's just not very likely, so it behooves people to at least have some backup plan for rain. The other side of this is that people will not remember the good forecasts as much as the bad, and the Weather Channel has business considerations in mind.
- He spends very little time on the question of how people act inside larger systems, where a given modeler might be more interested in keeping their job or getting a big bonus than in making their model as accurate as possible.
How much of the book do you suggest he devote to this? He addressed the issue directly, as the next couple paragraphs state. He also talks to quite a few institutional players at large organizations, both public and private.
- Having said all that, I have major problems with this book and what it claims to explain. In fact, I’m angry.
Really, stop with the faux outrage, because you don't seem all that angry throughout the post, you more seem to be disappointed he did not devote the book to your own pet topics. I find this kind of criticism to be mostly without merit. For me, there were three overriding themes in "The Signal and the Noise": Bayesian thinking (this being the primary one), the goals and motivations of forecasters, and examples of what forecasters have done right and what they have done wrong. I think it covered the bases pretty well, and it was an entertaining and lively read on the whole.
The financial crisis, at its heart was not an issue of "mistaken models". It was driven by (1) bad legislation from washington; and (2) unethical opportunism exploiting #1.
As a general rule, an Analyst at a Credit rating agency is a lowly position in wall street. Most important people (people acting of their own free will) disregard Rating Agency "analysis" out of hand. They do their own work. And people don't get promoted into Goldman Sachs, for example, from S&P et al very often. There is almosts a social stigma attached to the job, that would need to be cleansed with an MBA or some other "success" to pave the way. The people that cannot disregard rating agency work (due to law), of course are a built in market. And in general they are not on an even playing field with Wall Street with respect to their talent pool and access to information. So, bad analysis merely fills a vaccuum.
Using this as one example, think of the consequences. First, the model/analysis of the rating agency is a "product" looking to be sold (like a used car). There are no buyers for even the best analysis (wall st does its own research). So the "buyers" are not wall street but people who are forced to rely on credit ratings by law (eg, pension funds or some other public actors). But this is a captive market. The goal of the rating agency then becomes to game the system by extending the market. That is, creat new "protected classes" or create new "Asset types" that are salable to protected classes of investor. Structurally, now, this is the "game". The models, data-sets, and actual implementaions are really beside the point, provided there is a lack of transparency ("black box", proprietary, just complicated, etc). The models will be reverse engineered to "work", they only need to be "plasuble" (as in plausible deniability). Remember, the rating agencies are <<not legally experts>>. If they were, they could be sued, They are just expressing their 1st amendment rights <<to have an opinion>>.
None of this you seem to address in your commentary.
Nate Silver is just one in a long line of "experts" looking for ways to "sell their services". The first step in doing this is to never undermine the notion of "experts", or the idea that the system is driven by "expert knowledge". As the financial crisis has shown, those people who know what they are doing in the world are operating well beyond the scope and bounds of information that is available to people who publicly claim these hats. There is a reason hedge funds are famously secretive.
The underlying issue is my biggest peeve with both the buisness and political world. There is a popular viewpoint spread by many defacto authority figures that one should presume good faith from all groups involved, even though everything I can see tells me the opposite.
Did Silver decide to perpetuate that by being afraid to address the topic of malice in his book or did he fall victim to cultural attitudes himself? Either way this rant is all over the place, it complains about Silver mixing cause and effect while itself attacking a symptom, not the problem.
Edit: This post is written temporarily presupposing that the author is correct in her take on Silver's book, the comment by flatline in this thread hits some good points on why she may be a bit off. It was so long ago that I read the book I don't particularly remember how many inches Silver dedicated to incentives let alone care to debate if that was enough given the goals of his book.
That being said, the author has previous experience working on Wall Street as a quant, and is involved with the OWS Alternative Banking Group. She certainly comes with a strong perspective on the matter, but neither is she arguing out of ignorance of the system.
This is a pretty big deal.
Assuming good faith by authority figures is a popular and common fallacy from people who sit in the "Lawful" quadrant. N.b., I see this a lot in academic circles. Arguing from authority is the M.O. there, and assuming from authority is the consequence.
There's also assuming bad faith, a equally fallacious and (at least equally) popular idea from people who sit in the "Chaotic" quadrant.
We have to remember to have nuance in our opinions and dealings with others.
[[Call me “asinine,” but I have less faith in the experts than Nate Silver: I don’t want to trust the very people who got us into this mess, while benefitting from it, to also be in charge of cleaning it up. And, being part of the Occupy movement, I obviously think that this is the time for mass movements.]]
Ahhh, so she was part of the Occupy movement and comes from the world-view that the financial system and government is corrupt. She should have said that up front. Makes what she is saying make more sense.
Nate Silver doesn't believe those things, and so that largely explains why they come to different conclusions.
Until any contrary evidence, all Government is corrupt by definition (and yes, I call lobby-led politics "corruption"). In a true and free market "finance" is not corrupt, if you can't pay your debts you're out of it, this has been true since this industry was first invented by the Italians around the 1300-1400s.
In this latest crisis the problem was that the financial market was mostly led by Government-mandated decisions, starting with the Bear Stearns rescue in early 2008.
Like they say, money has no smell. Anyway, it's a very long discussion :)
What can I say? To each his own. I did not say that you, jeremyarussell, or any specific person taken "per se" needs a higher thingie to stop him/her from committing any crimes, it's just that for example the 20th century has been marked by some of the most heinous crimes in our existence as a species while in the same time only a small percentage of our fellow humans are psychopathic or sociopaths or however else you want to call those who commit crimes for pleasure only. Somehow, to make up for the difference (in the "people killed vs. natural-born-killers" ratio), I believe that we have somehow to look deeper into ourselves. Also pls. see this: https://en.wikipedia.org/wiki/Banality_of_evil.
And now that I'm reminded of Hannah Arrendt and the crimes of the 20th century, and for once to make a documented reference to Godwin's law on the internets (and to give people real reasons for down-votes), there's this little photo right here (http://imgur.com/PfM0e) of the Tiraspol (https://en.wikipedia.org/wiki/Tiraspol) train-station taken during WW2 by a German soldier. I paid around 0.50 euro-cents for the photo in an antiques shop (I live in Eastern Europe), around with other photos taken by the same soldier on the top of Eiffel Tower in occupied Paris or on the shores of the Aegean in Thessaloniki.
Now, those train tracks that you see in the photo at first don't signify anything by themselves, what with the peasant women waiting patiently for the next train or what-have-you. But if you happen to know (like for example I do) that tens of thousands (if not hundreds of thousands) of Romanian Jews (Romania being the country where I grew up and currently live in) were carried in trains to their final destination to close-by Transnistria (http://isurvived.org/Transnistria.html) then you begin to see things differently.
It took my country's Government close to 60 years to finally starting to acknowledge that we actually did exterminate people in Transnistria. Up until not that long ago there still was a statue of Ion Antonescu (https://en.wikipedia.org/wiki/Ion_Antonescu), the guy who ruled this country when all these, let's say really bad things happened, in a church's front-yard a couple of metro stations from where I'm now writing this comment. In fact, if I were to take the tramway to work tomorrow instead of the metro I would pass right by the said church (no statue of him now), which Antonescu actually helped build (the church, that is). Do you honestly think that church-building Ion Antonescu thought of himself as being a bad person?
And this is one of the many reasons why I think Governments do not deserve our trust.
Sorry for the long rant, now I can go to sleep :)
No worries about rants, I like reading them and trying to get myself to not just see another's point of view, but to own it, try and make it mine and get an even deeper sense of what's going on behind the words. And sleep well.
The naivete of which she accuses Silver is that Silver assumes that the modelers are striving for accuracy in their models (and that they failed to achieve accuracy). With some linked evidence, she asserts that the modelers in the financial industry knew that their models were inaccurate, but that those models supported the corrupt narrative that enriched them, and so perpetuated them. In other words, in the finance world (she says, with some apparent understanding and evidence) the wilfully inaccurate models were a means to a corrupt end.
The fundamental problem she sees is that incentives in the financial industry are not aligned with accurate models, that inaccurate models were deliberately used to further short-term performance at the expense of further inflating the bubble.
"most of the misallocation of capital was done by firms doing things like trusting AAA rated securities"
On this, she links to specific evidence that the "trust" they were exercising was knowingly misplaced because the incentive was always to get the next big bonus.
The way to improve the situation is to educate the consumers of those models (securities purchasers) about what models are best, and which are misleading.
It's more productive to say, "Buyer beware, sellers are misleading you in the following ways..." than, "Shame on corrupt sellers!". Silver's book is doing the first, which does not constitute defense of corruption.
Her criticism boils down to, "but there are agent-principal problems!"
But I think that's a bit of a sideswipe at Nate, who is dealing with a different domain of problem: modeling inaccuracy when the incentives ARE aligned in favor of optimizing predictive accuracy.
Sometimes the distribution that you ~can~ sample isn't really the distribution that you wish you could sample, and sometimes changing the prior in such a model is a way to make it behave as if it was sampled correctly to begin with.
She may be right. But Silver's larger point is evidence-based analysis. Where's the evidence to support her position? Why is her assertion any different than the political pundits' assertions? Is an email exchange between a couple of traders enough to prove global complicit awareness? There may well HAVE been global complicit awareness. But without enough data to statistically support her position, this response seems to prove Silver's point that we're better off looking at the data than we are working off what we 'know' is right.
At a murder scene, evidence is how one determines the cause and the killer, but if your killer has means he can manipulate that evidence. The issue we have now is that the murder (banks) are the group holding all the evidence. They don't want it looked in to, it would show they were an accomplice.
> "He gets well-paid for his political consulting work and speaker appearances at hedge funds like D.E. Shaw and Jane Street, and, in order to maintain this income, it’s critical that he perfects a patina of modeling genius combined with an easily digested message for his financial and political clients."
> "Silver is selling a story we all want to hear, and a story we all want to be true. Unfortunately for us and for the world, it’s not."
And of course, she derives also derives her income from speaking, consulting, and is writing her own book. She certainly benefits from positioning herself as a more expert Nate Silvers. "This best seller is wrong, buy my book to find out the details why" is pretty effective marketing.
By her own logic we should criticize her just as strongly.
Those who are attracted to financial careers often have a deep and abiding love for money, much like wolves have a deep and abiding love for sheep. Sheep farmers are smart enough to not to hire wolves as shepherds; but in the financial industry, the wolves are already in charge.
Saying that his book lacks detailed discussions of incentives (while true) misses the point of his book.
I wish every blog post included a line like this.