Search results

If you do a lot of backtesting with Kelly as your position-sizing (or optimal f, I would assume) you will probably see your system go through at least one drawdown of 90%+. If it recovers and makes a new equity high in the backtest, chances increase that your system has some value. Would it be...

Can f ever be larger than Kelly? The reason I ask is because that's the answer I got from an online optimal f calculator. I realize you're not responsible for everybody who sets up an online calculator and the results, but I'm curious. Right now, my Kelly is about 35%, but I'm getting an...

Didn't see this paper referenced anywhere in the thread. Seems like the failure rate for traders has been overstated, although I do find the result that those who trade the least and those who trade the most were the most profitable to be interesting. Seems like there is something to learn in...

The measure is clearly a proxy for something, even if it doesn't meet the strict definition you are putting forth as a requirement. Say what you want about Van Tharp (I'm not a follower), but the man clearly has a lot of data on trading and traders and when he says that the higher a trading...

You're not testing each individual trade, you're testing the set of trades, presumably only if they show a positive average outcome. If they have a negative average outcome, surely you'd reject the system unless you thought there was some value in taking the contrary of the system's signals, in...

Are you assuming you'd buy (or sell, if the trade is a short) on the open and close the trade on the close? I'm actually interested in running this test but want to make sure I understand the parameters.

First of all, no one would apply a statistical test to a trading method after 5 trades. Secondly, let's say you've reached a point where you have a large enough sample of trades to have some confidence in the statistical validity, the metric is designed to answer the question, "What is the...

So what if the system metric is impacted by stops and not solely entries? Risk management can be a "value-add" to a trading system and, if part of a conscious strategy, isn't random at all. Exiting a trade is just as much "market timing" as entering, as anyone who has ever taken a profit too...

Do you have anything to say other than personal accusations? I'm still eagerly awaiting the explanation of why my small, yet non-zero probability idea is absurd, other than that you keep on saying it's absurd, but bill's small, yet non-zero probability idea is not absurd. Let me guess, this is...

No, I pointed out how absurd bill's idea was with an equally absurd idea.

So, wait, Bill's idea, which was basically just the 180-degree opposite of my idea, and equally as likely (remember all that talk about "small, but non-zero probability") was some sort of stroke of insight, but my idea is "very stupid" or "crazy"? If you and bill want to mentally masturbate...

I thought I had made it pretty clear that this is NOT "the Van Tharp metric", it's a standard metric used in statistics for over a century. So, if your problem is that this is associated with Van Tharp, you need to just get over it. The main reason I brought up Tharp was to mention his point...

Here is what the OP originally stated: "I would like to determine the probability of my success being due to chance alone (and thus not my skill)." Whether you like Van Tharp, hate him, never heard of him, think drawdown is the most important statistic in the history of the universe...

Don't leave on my account. Clearly others value your input and there is no reason for you and I to interact in the future. It would have been quite easy to ask if I meant "average gain" in the sense you took it, rather than assume I did and then post some sarcastic comment. Especially since...

Then I'm glad I don't use his methods. Whew, that was a close one. Look, I didn't think the OP, who said he didn't have a lot of stats training, really needed to know that what I was talking about was a t-test, blah, blah, blah, so I put it in layman's terms. You got a problem with the...

I've seen your posts with the stats for your systems. There is no help I could get from you other than help stating the null hypothesis. You've exhausted your ability to help me already and I've only been here for a couple of days. I was happier when I thought I was going on your ignore list...

OK, then, the probability that you win every trade of over 100 trades in a random experiment is the same probability that Gisele will leave Tom Brady for a studly internet tough guy like you. Happy now?

I was online looking for system metrics and found it, not in one of his books, although I'm sure it's in one of them.

If you put me on ignore, that will only improve my experience here, I'm sure. Yes, it's possible that someone wins every trade with a random trade generator and it's also possible that Gisele will leave Tom Brady and come to live with me. Both are about equally likely. I didn't say the...

The easiest way to do it in Excel is to put the % gains and loss on each trade into a column and use the "average" and "stdev" functions on that column. It's just a quick and dirty figure that makes some assumptions about normality of the distribution, but I wouldn't worry about that for the...