How is "money management" for traders different from large fund management firms?

Quote from rvince99:

I KNOW that a matrix of probabilties of cross scenarios has less information loss than the simple, single metric of correlation -- particularly in the tails. I have written about this at length, performed ample studies on it, and have experienced the benefits and consequences of both, firsthand.

Suppose I have 2 components I am looking to allocate among. Say, 98 periods one component loses 1 unit, the other, gains 2 units (the subsequent period, the reverse occurs, the former now gains 2 units, the latter loses 1 unit. They keep flipping like this, with a net gain of 1 unit, for 98 perdiods. If this were the only data, our correlation coefficient would be -1.0). Then there is the one period where they both lose 10, simultaneously, and the 100th period where they both gain 10. My correlation coefficient in this case, over the 100 periods, is -.04753. That single parameter would be used to describe the relationship of these two streams -- yet, there is a lot of information going on in there -- some really BAD stuff two on that solitary period of -10,-10.

Contrast using this single metric with the notion of using a matrix of joint probabilities:
p A B
.01 -10 -10
0 -10 -1
0 -10 2
0 -10 10
0 -1 -10
0 -1 -1
.48 -1 2
0 -1 10
0 2 -10
.48 2 -1
0 2 2
0 2 10
0 10 -10
0 10 -1
0 10 2
.01 10 10

Which has more information? Which is more valuable on the disaster days?
This is only 100 days. The outliers in real life tend to occur far less than .01,
so your correlation coefficent, r, would typically be far more negative than shown here. (Incidentally, this matrix is the only thing one needs to gather to employ a leverage-space type model)
More...

What about using the Spearman Rank correlation? - Looks like providing a bit less information, but worth considering...
 
[[What about using the Spearman Rank correlation? - Looks like providing a bit less information, but worth considering...]]

Yes, that was my experience too -- but, (and contradictorily, if that is a word) the robustness of the Spearman r seemed to be a nice quality. It seemed to have the character of amending itself toward what the future might throw at us, more than the classic r.....and that might be just my own imaginings too.
 
A little bit more robustness at the cost of losing a very important piece of information: severity of change in addition to the joint probability of change. That makes it very tricky to use. Will require some sort of additional model for getting the magnitude-of-change measure.

All these: betas, spearman, correlations, etc, are variations on the same theme. If you are concerned about things that they don't describe, going from one to the other won't help you.

The deepest problem of portfolio risk management: people tend not to know what the question they actually want answers to is. Is it the severity of known losses, unknown losses, gap risk, leverage capacity, etc?

Quote from rvince99:

[[What about using the Spearman Rank correlation? - Looks like providing a bit less information, but worth considering...]]

Yes, that was my experience too -- but, (and contradictorily, if that is a word) the robustness of the Spearman r seemed to be a nice quality. It seemed to have the character of amending itself toward what the future might throw at us, more than the classic r.....and that might be just my own imaginings too.
More...
 
Exactly -- they do NOT know what they want. Not just on the downside (Is it variance? Is it drawwdown? What is it?) but on the upside as well (geometric growth optimality? Inreased average return?)
For answers to these very things, I turn to economic theory -- and jsut what makes people tick. (because, absent that, ...all we really know is that they tick!)
 
Quote from rvince99:

Allow me to preface my point here with this: About a year ago I began trading solely on the basis of arbitrary timing -- there is no fundamental or technical criteria to the timing of my trades. I have only traded equities and only from the long side, and have made upwards of about 30 trades. I have yet to experience a losing trade. My basis behind my trades has been entirely quantity-based as it is the only thing I have control over in this game.
More...

Greetings Mr. Vince... I read your books way back when the CME library was open to the public.. Your quote above begs a follow-up...

Scale Trading, Geometric adding to positions, Options spreads, Grail :confused:

Thanks,
Lakeside
 
Its simple -- but I won't get too specific as I don't owe anyone any more than that. However, my criteria has been to maximize being profitable, as opposed to maximizing profit itself.
 
... be careful there; It's great that you've been doing well with your purely dynamic sizing based strategy; Just want to offer the observation that CPDO type of dynamic strategies did GREAT for a year or two until Dec of 2007, where they lost billions. CPPI type and a bunch of other such strategies all had similiar experience.

When it comes down to it, there are only two basic "primary" form of dynamic sizing strategies: convex to market and concave to market. One will do will in trending, the other will do well in range bound.

Just make sure your have properly analyzed your strategy as opposed to just basically being long one type of beta that's been doing great in the current market environment.

Quote from rvince99:

Its simple -- but I won't get too specific as I don't owe anyone any more than that. However, my criteria has been to maximize being profitable, as opposed to maximizing profit itself.
More...
 
An interesting wikipedia article -- but it is not what I am doing here. My point is I am using the LSP model in a manner not to maximize profits, but to maximize the probability of being profitable at a given horizon in time.

This was an interesting discussion guys. Thanks.
 
You must log in or register to reply here.
Back
Top