BlueHorseshoe

Have you looked at ETFs at all? This could solve the leverage problem and I believe they're usually fairly easy to short (although I have no direct experience with them). BlueHorseshoe

Please note that the EL code given in the thread above is a square root formulation intended to increase the stability of the calculation. The change of decimal place in the gain factor is necessary for this purpose, but I have also found that it has the added advantage of increasing the granularity when the gain ratio is made to be dependent upon another value. Also, please note that the gain is an input in this code, and it is not therefore truly recursive. You'll find the formulation for calculating optimal gain on the wikipedia page for KF. BlueHorseshoe

Hi Tams, Do you think a mechanical end-of-day approach is practically unworkable then (apart from the risk of losing lots of money as you rightly point out)? BlueHorseshoe

Hello, If you're trading a mechanical method end of day then you could just get someone else to place trades for you - a friend or spouse or whatever. Provided they're set up to clearly recognise an unambiguous entry or exit signaland understand the importance of following the system then that might be preferrable to a broker. I did this for nearly a year with someone else placing trades because I lived somewhere so remote that there was no reliable broadband internet connection. Hope that suggestion is helpful. BlueHorseshoe

Nowadays you'd probably end up with 10,000 people each with 10 pieces of proof that the spam filter on their email account is working correctly. BlueHorseshoe

As a solution to the problem described in the posts above, why not just put a cap on the number of posts that any user can make in a day? No sane person is going to be making more than, say, half a dozen good quality posts per day. You could make some more active threads such as 'daytrading the e-minis' an exception, and also anyone moderating. BlueHorseshoe

If you'd like a PDF of the original Kaufman paper describing this indicator and its applications, let me know. However, I personally would recommend heeding the advice given by Tams. Keep in mid also that the AMA is an 'old' solution to the problems it addresses, and far more mathematically advanced approaches have subsequently emerged from the fields of signal processing and time series analysis. BlueHorseshoe

As far as the real world is concerned, I agree (I have never considered how this might apply to trading though). I think most would disagree - people tend to anthropomorphisize animals to a remakable extent. As Terry Eagleton put it, being a good human seems to denote something, whereas being a good toad means nothing - toads are just toad-like. You'd probably really enjoy John Gray's 'Straw Dogs - Thoughts on Humans and Other Animals', and 'Heresies - Against Progress and Other Illusions'. Glancing now at the wikipedia page on Gray, I'm suprised and enthused to notice that Nicholas Talib is a fan . . . John N. Gray - Wikipedia, the free encyclopedia BlueHorseshoe

Rande, are YOU trying to propose a rational argument against rationality? This is a first year philosophy student trap, where the tutor has a good old chuckle at the foolish undergrads (I once watched a hyper-smart pure maths bloke quibble for a full twenty minutes before admitting defeat) - I would have thought better of you! In all seriousness, you might enjoy Conrad's 'Lord Jim', as it argues a similar point/ BlueHorseshoe

Hi MM, Your recent short position described in the Euro thread was interesting for me because your exit looked like a short entry to me. The market looked short term overbought in a long term downtrend. In this instance I was wrong, or would have been stpped out as the market continued to rally. Over the long-run, however, my approach would turn a profit. I expect yours would also. Which approach is best? In the future, who knows? In the past, it's market dependent, in my opinion. In the Euro you can find a good risk:reward ratio entry, minimize risk, and let profits run. But letting profits run in a market that doesn't run is unlikely to be successful. In the Euro you're more likely to get a decent entry trading in the direction of a thrust in the market because a continuation is highly likely; in the ES, which is mean-reverting, price will probably go in the opposite direction to the one in which it is currently going, so buying when price is falling is often a better entry than buying after an up-thrust. In summary then, I think it's all market dependent. In some markets catching a falling knife is a good idea, in others you want to see the knife blunt and bounce from the table-top before entering. BlueHorseshoe

Hi Mitsubishi, Thanks for the 13 point plan - just so I'm clear, does the vendor wind up rich, or in jail, or both, at the end of all this? BlueHorseshoe

Hey, just because you're from Aus doesn't mean you get to slag off the NHS! My friend had one of these kits - apparently the trick is to start from the front and work towards the back BlueHorseshoe

To be honest, I was just keen to bring the thread back on topic! A few weeks back I had the misfortune to be stuck in Birmingham for an afternoon, so I called in a bookshop and bought 'Liars Poker'. I was struck by the extent to which Solomon's revenue reportedly came from 'sure things' - markets in which the other party might as well have been a two year old child. The author is essentially a salesman, and admits as much, but even the swashbuckling traders of the eighties are portrayed as the beneficiaries of the firm having spotted a 'mistake' that nobody else has spotted. Whether it's Solomon and CMO pricing, or Milken and Junk Bonds, they're pioneers in a new market that nobody else really understands. With everyone scrambling for opportunities, retail traders included, do these kinds of inefficiencies even still exist? The HFTs supposedly rake it in nowadays (ten years ago it was the Sta Arb quants), with their million-dollar IT systems - is becoming a Market Wizard getting more expensive? BlueHorseshoe

Winning odds | plus.maths.org BlueHorseshoe

The odds of a Tail after 99 Tails = 0.5 The odds of 100 Tails in a row = very, very small The odds of 100 Tails in a row after 100 Tails in a row = same as above The odds of 200 Tails in a row = very, very, very, very, very small As far as the original example was concerned, this is extremely simple probability theory. For any given event, the probability is 0.5. For any given sequence of events, the probability is derived from the sequential multiplication of the probability for each event. In this particular instance of a coin toss, the combinations and permutations are mathematically identical because the probability for every event is the same, i.e. if you ran a Monte Carlo the outcome probability for any possible sequence of a given length would be the same. Because very few of the possible combinations would demonstrate anything resembling auto-correlation, the probability of their occurrence is low. In random systems, the probability of anything resembling a pattern is small. This is a bit of a different scenario Obsidian, as one could assume that the accuracy of a shooter is dependent on how good the shooter is, rather than 50/50 chance. Also, if things like emotion or physical tiredness come into play, each instance may be causally linked, with the output from one event influencing the next. And although 'hit or miss' is Boolean, I'd be interested in how much the shooter was missing by before placing my bet. What am I saying . . . Of course I would just get the hell out of the way! BACK ON TOPIC . . . It is often said that if the markets were random and there were no exploitable edges, and hence the results traders achieved were random, then there should be far fewer Market Wizards than there actually are. A more interesting thing to consider is whether the number of Market Wizards who achieve success through anything that might resemble the kind of speculative trading that nearly everyone on this forum is engaged in, is anything more than a random model predicts. When reading books like Schwager's, it is obvious that some traders achieve success through 'sure things', or 'loop-holes' rather than 'speculatitive skill'. Arbitrage is an example of what I am talking about - because the arbitrageur and his risk-free profit exist outside of any system that could or could not be random, it seems to me that such Market Wizards cannot be counted towards evidence that the results of traders are non-random. Thoughts? BlueHorseshoe

Pretty much all financial price data is time series data (eg closing prices), so virtually any analysis you might perform will loosely fit this description. I'm guessing, however, that you're talking about techniques derived from signal processing and information theory? If so, then the MESA software website has numerous free articles by John Ehlers discussing these kinds of approach. Though I am sceptical of the validity of the approaches he recommends, he is extremely helpful in providing explicit code for things like fisher transforms, kalman filters, fourier analysis, least mean squares etc. The M.R. Bryant articles at the breakout futures website are equally helpful, and a little more diverse. The 'quant forum' is Wilmott, but you'd better be good at maths or it's all double-dutch. Ernie P Chan's site is useful, as is the archived Brett Steenbarger blog for simple ideas on data-mining applications. You might also find yourself dipping into neural nets, markov models, and genetic algorithms - all very exotic-sounding, but ultimately all just tools to do a job. Before even considering any kind of trading approach though, or selecting the time series analysis tools most suitable for it, you will want to uncover vary basic and general tendencies of price behavior in the markets you wish to trade. You'll need to determine things like the serial dependence of the time series, whether probability distribution frequency of the data conforms to a stochastic model and with what degrees of skew, kurtosis etc . . . Unless you either have a solid ground in statistics already, or find it sufficiently interesting to learn as you go, this mighn't be the best approach for you. On the other hand, it can be great if you like to be very quantitative about things. For instance, most experienced traders know that the Euro tends to exhibit more "follow through" or momentum than the ES; being able to describe it and measure it in precise terms of autocorrelation of the time series can be far more useful though . . . If you want any more help with resources then let me know. BlueHorseshoe

I don't know the answer to this. Could it possibly be to do with the supposedly diminishing speculative activity by the commercial banks? Maybe someone with a better understanding of macro economics etc will have the answer . . . BlueHorseshoe

Are you trying to propose a rational argument against rationality, MM? Isn't that rather like building your house on quicksand? BlueHorseshoe

Nope, but a PM from someone offering to help - once the code is fixed I'll post the solution here for anyone else who might find it helpful. Thanks, BlueHorseshoe

Okay, can anyone suggest an alternative way to find help on this? Thanks, BlueHorseshoe

Someone who works at the Bank of England told me that they weight all pound coins so that they always land in the bank's favour . . . The only way you can get an edge is flipping 20 pences, and apparently the Close of a Wallet is Meaningless . . . BlueHorseshoe

Do we get to keep the coins once we've flipped 'em? BlueHorseshoe

Hi ED, I'm in the UK also, although I don't watch much TV part froom the cookery programs. I may have explained myself poorly with the probability thing. The probability of the next coin flip being a head or a tail is indeed 50/50. But the probability of flipping eleven consecutive heads or tails are (0.5*0.5*0.5*0.5*0.5*0.5*0.5*0.5*0.5*0.5*0.5). In other words, the probability of an extended run of heads or tails (an outlier move) is very small. You can prove this to yourself very easily with a coin, and there's masses of academic literature to support what I am saying. The market regularly undergoes excursions that resist definition as a normal distribution. Moves in excess of two standard deviations are far more frequent than a gaussian model would predict. If you're interested in that kind of thing then the free articles by John Ehlers at the MESA software website might interest you. BlueHorseshoe

Yes, I'm guessing it's going to be something stupid like that and someone else will spot it instantly. :doh: BlueHorseshoe

Here is the code, with a logic virtually identical to that suggested by SIUYA earlier in the thread: MaxE=0; MaxValue1=0; For Value1=1 to 50 begin If E>MaxE then MaxE=E Else MaxE=MaxE; If P<Value1 and P[1]>Value1 then begin If M[1]=0 then M=1 Else M=M[1]; End Else M=M[1]; If P>Var2 and P[1]<Var2 then M=0; If M[1]=0 and M=1 then B=C Else B=B[1]; If M[1]=1 and M=0 then E=E[1]+(C-B) Else E=E[1]; If E>MaxE then MaxValue1=Value1 Else MaxValue1=MaxValue1; End; Plot1(MaxValue1); As far as I can work out this should return the value for Value1 that is associated with the maximum value for E. What am I missing? Why doesn't this work? I have been banging my head against a wall with this for several days now, so any help would be greatly appreciated. Thanks, BlueHorseshoe ps As per ZDO's suggestion I have done this 'manually' with code for a handful of values and it works perfectly - but I want to be able to run a wide range of values without needing pages and pages of repetitive code.