Contrary to popular belief and the Nobel prize committees, modern portfolio theory does not work for me. I prove it to myself many times. The testing is all wrong.
-------
(c) TonyP4 2012. Written in 1/12/12. Last updated in 1/12/12.
Disclaimer:
Do not gamble your money you cannot afford to lose. Past performance is a guideline and does not guarantee future performance.
All my posts are for informational purposes only. I'm not a professional investment counselor. Seek one before you make any investment decision.
Subscribe to:
Post Comments (Atom)
Marc said:
ReplyDeleteActually, I'm not sure it works for anybody. Back in my MBA days, my thesis was a critique of Markowitz and a study showing how much less effective it was then the supposedly less-sophisticated Shapre model.
In the late 2000s, I again had to deal with Markowitz and found over the years that the views I expressed a couple of decades earlier had become mainstream, with the modern literature referring to efficient frontier as an "error maximization" model. That is the problem. The model is perfect on paper, but the probability of getting reliable inputs is about zero. The efficient frontier garbage being disseminated today on some web sites and shareware programs presumes inputs based on historical data, which tend to be comically dreadful. More recently, a new variation was created, Black Litterman (Black refers to Fisher Black, the guy from Black Scholes) that tired to fix some of the mess. I didn't stay with that job long enough to get a chance to assess B-L, but anyone interested in efficient frontier should Google Black Litterman and take it from there.