FM Waves

This week I read my copy of “The Economist” August 18th-24th, and I found some articles about the most recent financial turnmoil which I’d like to comment, since there’s some info related to something I wrote here and here.

The Game is up (pp.63-64)

“Quantitative funds have been hardest hit [...]. Goldman Sachs admitted as much when it said that its funds had been hit by moves that its models suggested were 25 standard deviations away from normal. [...] That is silly.”

Of course is silly!, however, ex-post the probability of this whole thing happening is 100% (as the article explains, probability 1 is certainty).

Behind the veil (pp.65-66)

Talking about hedge funds:

“Insiders say losses were caused by a mixture of human and computer-driven error.”

How’s the split???. Was the error to use them models? (as a math believer, I want to believe NOT).

“…the complex models that drive them were up ended by the extreme market volatility. [...] the models went awry.”

Of course, they already said 25-sigma!!!.

“The saga has damaged the image of computer-driven funds.”

It’s a pity this could damage the image of whole OR as well. But that’s not the case…

“People aren’t going to give up their computers and go back to insider information and tips.”

And, I’d like to add up, at the end of the day the models were right, at least ex-ante ; ) .

Or not?:

“…highly unusual gyrations were ‘way out of whack’ with their models. Clearly the models were flawed.”

Hopefully, in another section of the magazine we can find an article about statistics and climatology; nothing seemingly related to these events but for a good insight about the difference between Bayesian statistics and Pascal statistical concept. Thought’d be interesting for understanding were the models could failed.
Remember the small print: “Historical performance does not assure future performance”. What a pitty!.

I’m not such a YouTube scubadiver, however sometimes I browse a little inside it. When I was trying to find something about game theory (remember my last post on Mr Smith vs Mr Nash) it came to my attention (not just to me but to an excess of 200k people) this funny…, what I’m saying?, hilarious video about the 10 basic economics principles from Mankiw.

YouTube

However, I have to say that what most godsmacked me was the resume of the guy: he’s actually an economist! (and as he says: baker & troublemaker). What the hell!, a real FUNNY ECONOMIST!!!. Congratulations mate!.

Dear Colleagues,

Last Feb-06 I was writting about “time for changes”, I was leaving UK and starting my new role in Brazil. Now it’s official: I’m leaving Brazil!!!, leaving the new world coming back to the old one, there in my beloved Spain. Following Mick Trick’s ideas: I think I was far too deep into my comfort zone. There are so many reasons, beware I’m not saying I’ve taken my decision because I’m so (un)control freak!. Anyway, FM Waves moves again: moves from the country, moves from the job, moves from the sector.

Well, I’m very happy, because I see so much blue sky, the Spanish sky.

Good, I’ve been able to survive to 100 posts!. During all these years I’ve been (at least I think I’ve been) writing about economics, technology, and operations research, mainly about OR. It’s been two countries: UK (”operational research”) and Brazil (”pesquisa operacional”); however, I’ve been sticking to the american “operations research” (as INFORMS suggests), although as an Spaniard I know it as “investigación operativa” as well. So, three countries, four names, loads of fun!. Don’t forget “economics”, “economía”, and “economia” (in valencian language; yes, my mother tongue).

As my little celebration I’ve extended the “About” page adding information “about the blog”, and, following the idea from Javier Llinares, some info on the main stats. KPI’s?: I’m embarrassed about mine, but, life’s life.

While I’m trying to juggle around with the data set offered by Netflix for the quest of improving their Cinematch algorithm I’m in my own quest for getting the theory behind the real model, the structure that resides behind those 2GB of user and movie ids, dates and so on.

Years ago I co-authored a paper about tastes and preferences, so I liked to carry on with this research, in order to give light to the matter (i.e. 40 movie features can be resumed in just one, “the rating”; people’s ratings are inconsistent; blah blah blah); by the way, it’s because, at the end of the day, ratings are just a set of preferences (ordinal, transitive, reflexive, but are they complete?). This doesn’t mean I’ll stop researching through machine learning, but that I’m opening two fronts.

For those fighting along my side, I’d recommend the following readings:

_Varian, H. (1992). Microeconomic Analysis. W. W. Norton & Company; 3rd edition.

                 Chapters: 7 (Utility Maximization), 8 (Choice), 19 (Time).

_Rabin, M. (1998). “Psychology and Economics”. Journal of Economic Literature, Vol.XXXVI, pp.11-46.

_Rieskamp et al. (2006). “Extending the Bounds of Rationality: Evidence and Theories of Preferential Choice”. Journal of Economic Literature, Vol.XLIV, pp.631-661.

It doesn’t mean these articles are going to help solve the problem, however are going to help understand why when we do this this and that, the result is such a given RSME.