Recent content by SplawnDarts

You can test a lot longer than a few weeks with replay if you have the right data. And the data format is pretty obvious, so pretty much any data can be made into the right data with a little effort. No test environment does long tick-driven tests with variable parameters etc - it would take...

NinjaTrader does what you're describing.

The math of Topstep seems simple: They cannot possibly lose unless they deem you to pass the combine. You cannot possibly win unless they deem you to pass the combine. On that basis alone you can deduce what their policies, both stated and unstated, will be. And from there you can deduce what...

What's the charting/execution platform?

There are definitely professional sports handicappers. Moreseo in Europe than in the US - it's easier to get a big bet down with a reputable firm on the other side of the Atlantic. It doesn't actually take killer stats to deal with some sports. Pro football and basketball can be tackled with...

Don't bother working on reading comprehension now, but this has already been dealt with.

I use three custom indicators - one counts things on the tape, one does some linear regression math, and one is a more statistically rigorous take on Bollinger bands. Bollinger band (or my custom take) are modestly interesting to look at, but I've never seen any evidence in testing that...

One other heads up - if your trading style has situations where large losses or wins can occur - much larger than the win/loss averages - then you need your sample to be big enough to include several examples of those. In contrast if your losses are bounded by relatively tight stops+slippage...

Glad I could be of help. If you want confidence on a method with non-symmetrical wins and losses, replace the binomial probability of 0.5 with whatever would be required to break even - (AVG_LOSS)/(AVG_WIN+AVG_LOSS). So if you won 1 unit and lost 2, you would put in 0.666. The number...

You can answer your own question using the cumulative binomial distribution in Excel or similar eg. =BINOMDIST(85,132,0.5,TRUE) Note that the number of heads is reduced by 1, since you're summing up the probability of a worse performance and should stop there, not at 86. 99.97% of results, if...

This is true for all learning system approaches (NN/back-prop, genetic, support vectors, etc.). Their inability to find trading methods that are known to work on the data used for training is amazing to watch.

Well ET seems to have more scam vendors and their shills than traders, so it stands to reason they're not affected. That said a decrease in order flow is a smaller problem for small traders than it is for big traders for obvious reasons.

Value of commentary: negative.

Fact: several major banks are major market makers in ES and ES options. Value of your commentary: negative.

Funny - I'm seeing a big drop in savvy liquidity consuming participants in ES and a few other markets. From my perspective, opportunities are opening up left and right. I guess the banks' loss is my gain.