Glen, Yes, how people build bad models. Getting back to Taleb's point with the 'black swan', that he should have stated more clearly, that it's always dangerous to do complex analysis with fat tailed distributions. You might be still more clear about it by making a list of behaviors that become complex and fat tailed to watch out for. That includes things like growth and collisions and changing distributions generally that progressinely diverge from their original behavior, and all suggest that the system being modeled isn't the same anymore. Covering that up with an easy tweek of the noise factors in a model then doesn't address the problem. ;-)
Phil Sent from my Verizon Wireless BlackBerry -----Original Message----- From: "glen e. p. ropella" <[EMAIL PROTECTED]> Date: Fri, 03 Oct 2008 12:24:53 To: The Friday Morning Applied Complexity Coffee Group<[email protected]> Subject: Re: [FRIAM] Bernanke's Financial Modeling Technology Thus spake Robert Holmes circa 10/03/2008 12:15 PM: > Look at this way then - if he'd had access to a zillion parameter > mega-simulation, do you think we'd all be safe and cozy and *wouldn't* be in > the middle of a financial crisis? [You guys need to trim the cruft off the bottom of your e-mails.] I think we would be in a better position. If nothing else, the existence and use of zillion parameter mega-simulations _force_ us to concede that models are often wrong and useless. Granted, there are still morons who think that there _can_ be accurate or True models. But if more people in powerful positions knew, tacitly, how bad most models are, they would be much more suspicious of their and others' policy decisions (which are all based on models of one sort or another). At least these guys had the sense to reify their models in some way, rather than merely shooting from the hip and listening to their gut. You gotta give them that much credit. We may not avert crises; but, we might soften them considerably. NPC: a, b, and d are satisfied. (c) might be a stretch. [grin] -- glen e. p. ropella, 971-219-3846, http://tempusdictum.com ============================================================ FRIAM Applied Complexity Group listserv Meets Fridays 9a-11:30 at cafe at St. John's College lectures, archives, unsubscribe, maps at http://www.friam.org ============================================================ FRIAM Applied Complexity Group listserv Meets Fridays 9a-11:30 at cafe at St. John's College lectures, archives, unsubscribe, maps at http://www.friam.org
