Tim, Aptus, anybody: Testing Testing......
Interesting that this testing comes up all the time and again. Fair enough but I see two problems. I will try to be short:
1) Between 1987 and 1992 I played around with my version of Aim and thought I would, at the flick of my finger, set up a formal mathematical model in the way I might have done it for a process in a pulp mill of a engine design office. I tried to grasp the AIM structure in terms of curves, differentials, integrals, and I thought this AIm Cat would be skinned in a month or two.
2) Although I think I know a thing or 2 about mathematics, maybe 3, the task completely eluded me and escaped between my fingers: I could neither formulate the input and the various parameters(Like Aptus noted), nor the output into any understandable or analysable structure which would lend itself to systematic analysis. I gave up for all I saw a chaos.
Admittedly, professional mathematicians would no doubt get a lot farther in this effort than I could then or now. The thing that stumped me was the discontinues nature of the data. I was used to machines, temperature, time etc. that by nature, or by virtue of simple assumptions, were continuous variables. No. discontinuous jumps in the vale function and the PC that occur with the buys and the sells. Thinking about it makes me want to give up again, although I havn't even started.
To get going on his one needs an unlimited passion for solving this problem, a high level of mathematical knowhow for analysing discontinuous functions and knowhow of numerical analysis techniques. On top of that one needs to know how he would test the formulations to make sure that the proposed processes models are useful, before you would start the real testing or optimising.
We all know that volatility is needed. No Analysis is required for that. One needs to be able to justify the analysing/testing process that we think will be useful(whatever it is). I saw visions of a NASA-Like Team of experts turning the wheels of the project. A large Budget that any University professor would be proud of would be required to fund the research. And then: How many people would pay for this know how in the future?
I do not think that such a formal in-depth attach will ever get off the ground, nor do I think that it will be worth the trouble.
I wouldn't mind being proved wrong on this.
Conrad
AI
