And Jack, I have studied you. Oh, I how have studied you! But the Tathagata admonished us all to "Be lamps unto yourselves", so alas I must go my own way. As always, you see through my slight and facile offerings. Were we to meet (inadvisable, we might both have strokes), I would teach you my Foosball theory of trading. My main screen is in fact quite similar to a Foosball layout, but with many more paddles and players.
How did this become a Hershey thread? Reread the title: Estimation Theory Trading. It is about how trading is like toilets. Or washers and dryers. Or humidifiers. In the details, it is about the tradeoff between the excitement of risk taking and the comfort of reliability. Achieved in a control theory context where the tuning can dial between those extremes. As usual, I am talking to myself. Screw it!
Champignon, there is a universe of estimation theory analytical tools older than your grandmother. With every post you reveal how superficial you are intellectually. There is nothing peculiar about applying mathematical tools to trading. Need I remind you that Sir Isaac Newton was also Chancellor of the Exchequer? As to my own mental health, you are free to ignore me if I disturb you. Just as you ignore out of lack of relevant background what my initial post said. My guess is that if I research you, you have never posted a single trade or blotter here, so you have no credible platform from which to criticize me.
High Potty Miss, the proposition of your opening post is such that you ought to have been open to both its practical and theoretical flaws. You think you have such an amusing mind, why don't you show us that you are smart enough to demolish that proposition. Otherwise do you refer to your silly little blotters of selected success. Post a summary of your riches from trading over the many years you've been posting drivel on ET. But then again you have admitted elsewhere, haven't you, that you are just a piker who trades one lot now and again.
Your conclusion regarding laplacian operations is slightly misguided. Laplacian transforms/kernels/operators (whatever one chooses to call them) work well with "spiky" data in general due to their mathematical structure. While causality (the result of a catalyst) may be the cause behind the spike, the price inconsistency is what one is really dealing with. A laplacian transform allows for much lessor approximation error for such "sharp" price functions - i.e. gaps and all other severe "shock" type inefficiences. There exists a broad range of work on this type of modeling in the computational intelligence field. If you have the inclination or the time, lookup "laplacian standard additive model" on google and do some reading. Its neat stuff and I spent a lot of time working on it a few years back. The financial modeling applications are many, especially for volatility modeling. However, in terms of a good trading model - I have yet to find something truly robust and tradeable - as another poster mentioned earlier, the lag is what makes these types of models ineffective, they rely too much on history. Regards, Mike
Mike, thanks for your informative comments. I merely meant that Laplace transformation is appropriate because it is single-sided to be in accord with the causality requirement of functions of time. My sole background in Laplace transformation is in the analysis of waveforms for filter synthesis, and no doubt I am woefully out-of-date. My experience is that treating price series as if they were time series measured from physical phenomena is a useful approach if used with caution, understanding that price is not bound by the constraints of physicality. In regards to "robust and tradebadle", does a young mathematical buck like you have any hints for a broken-down old innumerate like me? Best regards, and thanks for the reference.
LPT works symmetrically on odd and even harmonics (the fundamental is the carrier when it comes to making money). If you look at nerve transmission stuff (theory and pragmatic cures), you may find that steady state (making money at a given velocity) coresponds to a steady stimulation of receptors whose signal is antenuated down stream to allow the decision making system to focus on either what wasn't that or a delta in stimulation.
Ah, yes, the old negative side lobes trick for local area suppression. Nature evolved it before we discovered it. And you employ it as a mental trick to concentrate on detecting change, letting continuation take care of itself. Of course I pervert everything you say, so what I learned from you was to focus on continuation and to be surprised by change. Helps me stay in a trade longer. I use a five sample correlation to detect the end of continuation, if not necessarily the beginning of change. There we differ, as I don't regard the end of of continuation as the beginning of change. Perhaps an artifact of my one-minute orientation. But your paradigm of continuation and change is a very powerful one.
The thesis of this thread apparently has eluded most of ET judging from the mostly negative responses (those few positive responses are much valued). So let me put it another way that most of ET can understand. Trading is all about character, or the lack thereof. Traders who fail generally cannot follow rules because they are persons of low to no character. But being onesuch myself, I think we moral bankrupts deserve to win just as much as those of high moral fibre. Our saving grace is that we CAN take orders when closely supervised. My control theory systems provide that supervison and give those orders. Red light short. Green light long. Orange light stand aside (yellow being bit difficult to see on the screen, and this command being the most important in terms of not losing money). So ye of low character (both ye and we know who you are) may rally around me in this effort to make trading profitable for reform school graduates as well as boy scouts.