Evaluate function of Alice4b from B�rsenhackerbuch

Posted By: Dalla

Evaluate function of Alice4b from B�rsenhackerbuch - 04/27/17 13:35

I found a reference to Alice4b in another thread related to detrend I believe. This is the snippet I'm referring to:

Code:

function evaluate()
{
	var TestProfit = 400;
	static int Count = 0;
	if(Balance > TestProfit)
		Count++;
	
	var Bucket = floor(Balance/25);
	plotBar("Profit",Bucket,25*Bucket,1,SUM+BARS+LBL2,RED);	

	if(TotalCycle == NumTotalCycles) {
		var Probability = (100.*Count)/NumTotalCycles;
		printf("n-------------------------------------------");
		printf("nReality Check: %.1f%% Random Probability",Probability);
		if(Probability <= 1)
			printf("nSystem result is significant");
		else if(Probability <= 5)
			printf("nSystem result is possibly significant");
		else 
			printf("nSystem result is not statistically significant");
		printf("n-------------------------------------------");
	} 
}

I'm wondering about TradeProfit = 400, which guides whether the system result will be considered statistically significant or not. Were does this value come from?
Is there some reasoning behind the selection of this value? I realise this might be explained in the book, but since I don't read german I'm out of luck :-(

Posted By: jcl

Re: Evaluate function of Alice4b from B�rsenhackerbuch - 04/28/17 12:52

400 was the profit achieved in the test with the real price curve. For getting its p-value, the 400 must be compared with the random results.

Posted By: Dalla

Re: Evaluate function of Alice4b from B�rsenhackerbuch - 04/29/17 03:50

Ok, so the reasoning is that if we shuffle the price curve, the system should deteriorate. If it doesn't, we have not really found an edge? Simple variant of WRC?