| Wednesday,
September 17, 2008 REMEMBER! Friday
September 19 is International Talk Like a Pirate Day! Arrrr!.
I have several letters recommending
THE FOURTH
QUADRANT: A MAP OF THE LIMITS OF STATISTICS
[9.15.08]
By Nassim Nicholas Taleb
http://www.edge.org/3rd_culture/taleb08/taleb08_index.html
Statistical and applied probabilistic knowledge is
the core of knowledge; statistics is what tells you if something is true,
false, or merely anecdotal; it is the "logic of science"; it is the
instrument of risk-taking; it is the applied tools of epistemology; you
can't be a modern intellectual and not think probabilistically—but...
let's not be suckers. The problem is much more complicated than it seems
to the casual, mechanistic user who picked it up in graduate school.
Statistics can fool you. In fact it is fooling your government right now.
It can even bankrupt the system (let's face it: use of probabilistic
methods for the estimation of risks did just blow up the banking system).
The current subprime crisis has been doing wonders
for the reception of any ideas about probability-driven claims in science,
particularly in social science, economics, and "econometrics"
(quantitative economics). Clearly, with current International Monetary
Fund estimates of the costs of the 2007-2008 subprime crisis, the banking
system seems to have lost more on risk taking (from the failures of
quantitative risk management) than every penny banks ever earned taking
risks. But it was easy to see from the past that the pilot did not have
the qualifications to fly the plane and was using the wrong navigation
tools: The same happened in 1983 with money center banks losing
cumulatively every penny ever made, and in 1991-1992 when the Savings and
Loans industry became history.
[Emphasis added]
Taleb is the author of The Black Swan,
which I reviewed in June. I don't call many books or authors important;
both Taleb and his book are important and if you have not read The Black
Swan you really ought to. His new essay applies his principles to the
current financial crisis. And keep remembering: the people who did not pay
attention to The Black Swan have just lost more money than all the banks in
history have ever made from risk taking investments. And they were quite
certain they were the smartest guys in the room.
==
I set that up last night before I went to bed. It seems
appropriate this morning. The government is bailing out AIG, and the
government is running the company. I wonder if the people running it for the
government will be paid millions and millions.
Think about it. Due to Barney Frank, Fannie Mae and Freddie
Mac were able to lose more money and transfer more money to the
stockholders, executives, and of course the recipients of campaign
contributions and lobbyist favors. How in the world is it in the interest of
the US to have outfits intended to facilitate "affordable housing" be
allowed to make enormous risky loans, bundle them in with other loans, sell
them off, and use the proceeds to make even more risky loans? Is this a way
to get the middle class into affordable houses? Is loaning money for a
$475,000 house to an illegal immigrant who makes $25,000 a year as a
gardener in the national interest? And should those who authorized those
loans be rewarded?
=================
Subj: Statistical methods and the Two-Span Bridge of
Inference
John Tukey used to say that every bridge of
statistical inference has two spans. One is constructed of data, the other
is constructed of assumptions. If the data-span is longer, the
assumptions-span can be shorter, but there are always at least *some*
assumptions. It's important to understand what those are and how much of the
structure depends on them -- and will collapse if they fail.
I recall Herman Kahn writing something similar about
Systems Analysis. The right use of SA is not to make prophecies about what
will really happen in the future, it's to make explicit the assumptions the
decision-makers are making and to explore what might happen if some of those
assumptions turn out to be false.
Rod Montgomery==monty@starfief.com
Hurrah. And precisely. I once spent a weekend with Tukey at
a live-in conference, and since I was there with Minsky we ended up having
breakfast with Tukey quite a bit. I was much impressed and have read most of
his works since. Boeing hired Herman Kahn to come teach the techniques of
systems analysis to the systems analysis staff which included me, and that's
probably the most important lesson I got: that the process is mostly useful
to show how you came to a decision and what assumptions they are based on. I
have Herman's book Techniques of Systems Analysis; it's a RAND document and
I think has not been published elsewhere. My attempts to find it at the RAND
site have failed but it may be I am not all that good at such searches. I
would recommend the book to anyone involved in complex decisions.
=================
What's the way out of the financial dilemma? Well, first,
understand that consumption is not adding to PRODUCT even if economists
think so. Making ever more risky loans never was a way to increase wealth
even though it showed up in the GDP estimates.
We have to start making things. In my case I make stories
and novels. I may also make tomatoes this summer: I have a bit of land. At
one time I had a hydroponics setup here and produced a lot of vegetables; I
am a bit old for that now, but for a modest investment (I used gravity and
lifting buckets rather than pumps) I was able to make beans and tomatoes
that didn't show up on the GDP but couldn't be taxed either.
American have got to understand that moving money around in
circles is not actually production; that most "services" in the service
economy aren't actually need or producing much -- did we need 100,000 sales
agents for high risk mortgages that put illegal immigrants into $400,000
houses on interest only loans? Sure there are real service jobs, like
mechanics and plumbers, who take things that don't work and make things that
do work, but that's not the same as selling bad mortgages to people who
shouldn't be borrowing money in the first place.
Spengler is an astute observer of the US economy, and in his
essay on Lehman Brothers and the crisis
http://atimes.com/atimes/Global_Economy/JI16Dj08.html
has some observations worth your attention; and
over in mail we have a
couple of letters worth your while. The fundamental principle, though, is
that before you can have distribution of products, you have to have products
to distribute. Borrowing money on rising housing prices to buy Chinese goods
doesn't produce much that can be seen.
We need to make things. Produce things. Create wealth, don't
just move money around in circles. Of course the smart people understood
that making things isn't the thing to do: the Lords of the Universe are
those who sit in offices on Wall Street.
But we stand here representing
people who are the equals before the law of the largest cities in the state
of Massachusetts. When you come before us and tell us that we shall disturb
your business interests, we reply that you have disturbed our business
interests by your action. We say to you that you have made too limited in
its application the definition of a businessman. The man who is employed for
wages is as much a businessman as his employer. The attorney in a country
town is as much a businessman as the corporation counsel in a great
metropolis. The merchant at the crossroads store is as much a businessman as
the merchant of New York. The farmer who goes forth in the morning and toils
all day, begins in the spring and toils all summer, and by the application
of brain and muscle to the natural resources of this country creates wealth,
is as much a businessman as the man who goes upon the Board of Trade and
bets upon the price of grain. The miners who go 1,000 feet into the earth or
climb 2,000 feet upon the cliffs and bring forth from their hiding places
the precious metals to be poured in the channels of trade are as much
businessmen as the few financial magnates who in a backroom corner the money
of the world.
That, of course, is Bryan's
Cross of Gold speech.
There was some wisdom in it, which is why it impressed people and won Bryan
the nomination (but not the election) for President. I would add that those
who write software, build computers, make diaper pails, sew clothes -- well
you get the idea. And yet we enrich people for gutting the factories, firing
the workers, and sending their jobs overseas.
I said a while ago that if our schools taught people on the
left side of the bell curve things they might actually do instead of making
them endure college prep courses designed to allow them to go to college
which most will not, we might yet have a thriving economy -- particularly
now that transportation costs are so high. One friend said that was silly --
there isn't anything for those people to do. There are no jobs for those
with IQ below 100.
That's silly on the face of it: if it were true why would
there be so much resistance to closing the borders? We are importing
unskilled laborers by the tens of thousands. But it's dead wrong in another
way: there is no reason why American ingenuity can't manage to make American
workers productive at making the things we now import from China (and borrow
the money in order to pay for them; if they were made here the money would
stay here, no?) We actually are smart enough to do these things.
Of course we won't. The schools won't reform, and the
education system will continue to be designed and ruled by people who either
don't know the students or don't give a damn about them, leave the classroom
teachers stuck with No Child Left Behind to try to get more IQ 85 students
to get a passing grade in algebra rather than teaching them something they
might actually apply to their future lives.
And so it goes.
=====================
Monty found this:
Herman Kahn's Techniques of Systems Analysis
http://www.rand.org/pubs/research_memoranda/RM1829-1/
Available on line as a pdf file.
However, I have had real problems trying to download
this. In Internet Explorer an Adobe reader opens, the file downloads, and I
can read it but I cannot save it. In Firefox the system blows up. I am
beginning to be really annoyed with Firefox which seems unable to do
anything but tell me about how wonderful Yahoo is, and send me unwanted
popups about Yahoo, and in general not work very well if anything associated
with Adobe and pdf is involved. It's enough to get me to Internet Explorer,
except that I can't save the file I have downloaded. Now I have copies of
Harman's book, so it's all right for me, but I am not sure how well that
link above will work for you.
I do say that all those interested in decision
making will profit from reading this ancient document.
I am going to restart my machine and see if that
makes Firefox work better.
All right. By installing pdf download, a Firefox
extension, and then RESETTING MY VISTA COMPUTER, I seem to be able to handle
pdf files in Firefox. I'm still learning. But I am not happy with Yahoo
popping up stuff I didn't ask for.
============
ENOUGH on the Kahn downloads!!! Thanks. My problem
was that I needed to add something to Firefox, then restart Firefox only it
wouldn't restart without resetting the whole computer. Once I did that I
seem to have what is required to handle pdf files. I already had the file; I
just wanted to test the download.
In any event I very much recommend that anyone
interested in decision making get the document and read it. Herman was a
great teacher. I learned a very great deal in the week he spent coaching us
at Boeing. I later worked with him on other matters. As a result of my
recommendations Robert Heinlein spent a couple of weeks at the Hudson
Institute, and became friends with Kahn.
Anyway thanks to all. And this works:
http://www.rand.org/pubs/research_memoranda/RM1829-1/
It isn't the first time it has been listed on this
site, but my memory isn't always so good.
====================
Incidentally, Roland and other Mac people remind me
that Firefox handles pdf files in a Mac without these problems. Having said
that, I have to say that if you add the proper extensions, Firefox works
well with Vista. And then I learned:
Saving PDF Files
I am sure someone has already
told you this, but in case they haven't, to save a PDF file from a web
site right click on the link and then left click save link as in the
context menu.
Bob Holmes
I am sure I've known this and forgotten it. Savc
Link As actually saves the file, not the link. I suppose that is obvious
to everyone but me. So I relearn something every week....
Fortunately it's not Alzheimer's. But I do feel a
bit like the absent minded professor sometimes.
Think of this as a pledge drive. My bills from my ISP
have come. Not onerous, but I still have to pay them.
It takes time and money to keep this place up. If you want
to keep this site open:
For platinum subscription:
Platinum subscribers enable me to work on what I think is important
without worrying about economics. My thanks to all of you.
Patron Subscription:
Wednesday TOP
Current Mail
|
