Bayes Rule - 65% certainity of S&P down 10% soon

[winner69]

Just for Enumerate and Halebop

Some geeky stuff for you guys ...

http://www.hussmanfunds.com/wmc/wmc070129.htm


(excerpt) Bayes' Rule currently puts the likelihood of a 5% or deeper market correction beginning within the next few weeks at near certainty, the probability of a 10% correction starting during the next 13 weeks at about 65%, and the probability of a bear market beginning within the next 6 months at over 75%. There is, of course, no such thing as certainty in the financial markets. Suffice it to say that the probabilities aren't good.

[skinny]

As someone who uses Bayesian methods I must say that was a pretty dissapointing article - an academic would say verging on the dishonest. The problem is that P(E|~X) is close to zero over their historical sample and given how the evidence, E, is defined. As such, it leaves me suspicious that the authors have simply gone through a data minining exercise to uncover a set of conditions (i.e. E) that maximises the X event (in this case a market dowturn.) Its a noromal classical statisitcs exercise, but doesn't really feel Bayesian.

[Halebop]

Thanks Winner I consider myself geeked!

I haven't been particularly bullish on markets for the last 12+ months so he might find a ready market in me just so I can feel vindicated! (My "bearishness" and defensiveness has literally costs me plenty in reduced profits / opportunity cost of inaction where I have taken smaller than normal bites of what proved to be highly successful investments and although I think I'll beat the indices this year it's a closer race than it has been in years).

Like Skinny, have some doubts about making assumptions before reading the data. It's real easy to find trends that don't really exist that way. ...But if he's right then I'll be right too and I'll get to bask in the glory of my year too early call... mwahahahahaha, so very clever, victory is sweet etc...

...An interesting read all the same.