Backtesting Metrics

Quote from Mike805:

The posters you're addressing don't even know what a regime shift is...

Mike
More...

How do you like clown to constantly insult and underestimate the intelligence of other people?

"regime shift" is not a finance technical term you clown. It is used in Ecosystems study.

A true regime shift will be when you stop posting nonsense here you clown and stop underestimating the intelligence of other posters.
 
Quote from HowardCohodas:

My trade filled, so I'm back.
More...

I wonder how you can trade while constanly posting TO at least Two different forums, ET and T2W, simultaneously. CAN YOU TELL US THE SECRET? ARE YOU THE NEW SUPER-CHARGED POSTING MACHINE? ARE YOU A HUMAN OR A FORUM BOT?
 
Quote from dave4532:

How do you like clown to constantly insult and underestimate the intelligence of other people?

"regime shift" is not a finance technical term you clown. It is used in Ecosystems study.

A true regime shift will be when you stop posting nonsense here you clown and stop underestimating the intelligence of other posters.
More...

Ahh yes, the queen troll chimes in. Good job dave. Nice post. You're apparently the authority on all terms "financial".

Here's a question for you dave: do you actually trade and are you profitable? Simple yes/no will do.

Edit: FWIW, my estimation skills are pretty sharp. So far your intellect sits somewhere around that of a parrot.

http://en.wikipedia.org/wiki/African_Grey_Parrot

Take a look at the "Mimicry and Intelligence" section. Quite fitting IMO.
 
Quote from Mike805:

Ninna,

With an intended lack of respect to those you're addressing; you're talking to a few clowns in this thread. The range of belief systems held on ET can be quite diverse, unfortunetely, when it comes to these topics, most choose to betlittle information if it goes counter to their limited experience base.

Point in hand, no one should trade a strategy that doesn't survive in all regimes, no matter the frequency. It's about confidence in the model. If one is putting on large positions, it comes down to confidence in the process one took and the method that resulted.

The posters you're addressing don't even know what a regime shift is...

Mike
More...

You, sir, are a jackass...

What's a regime shift? By your definition it may be a fundamental change in the nature of the markets. But there are regime changes of varying magnitude. The markets are always changing. Yet they are always the same (wow, I'm getting Hersheyesque)...

The performance of the stategy will be inversely proportional to how tightly fitted it is, up to a point. There is a sweet spot. Fit it too tightly and you're just fooling yourself and will get results nowhere near the in sample test. Fit it too loosely and, well, you can look for something that would work at all times, in all markets, etc. But it wouldn't likely be a very good strategy.

Do you know why?

As a final note, how do you really know WHAT I or any one else here knows?

You don't. You really don't know shit. Just making assumptions. Yes, there are a lot of idiots on here, and I think I've just identified another.

Let's hear about your knowledge of math, data analysis, trading experience, etc. Where'd you get your PhD in stats, which hedge fund are you running? I'm sure that I've heard of it...
 
Quote from iagainsti:

You, sir, are a jackass...

What's a regime shift? By your definition it may be a fundamental change in the nature of the markets. But there are regime changes of varying magnitude. The markets are always changing. Yet they are always the same (wow, I'm getting Hersheyesque)...

The performance of the stategy will be inversely proportional to how tightly fitted it is, up to a point. There is a sweet spot. Fit it too tightly and you're just fooling yourself and will get results nowhere near the in sample test. Fit it too loosely and, well, you can look for something that would work at all times, in all markets, etc. But it wouldn't likely be a very good strategy.

Do you know why?

As a final note, how do you really know WHAT I or any one else here knows?

You don't. You really don't know shit. Just making assumptions. Yes, there are a lot of idiots on here, and I think I've just identified another.

Let's hear about your knowledge of math, data analysis, trading experience, etc. Where'd you get your PhD in stats, which hedge fund are you running? I'm sure that I've heard of it...
More...

There's decent content in your post. But, you did initially dismiss Ninna's point, right? And for someone who seems to know what you know, that seemed dense didn't it? I called you out on it because Ninna is right and you're wrong in calling it "bullshit".

What Ninna is describing, the 97-98 effect is fairly well known in general as a regime shift. The prescribed reasons are varied, but, most agree it was of a fundamental nature.

Now, how would your strategies work in such an environment? Do you have confidence they'd remain in tact?

On to your questions about me; well, first off, you're a new poster. I've been here for a while. Second, yep, got a grad. degree under my belt (not in stats, but in a real science). Third, actually I do run what some call a fund, I make it point that no one hears about it. My experience... well, its kinda long winded.

Good luck to you. Maybe this thread will cause you to test around around that 97-98 mark. It wouldn't hurt to do so, would it?
 
Quote from DustyFoot:

Hi Everyone. I have been working on developing several ATS and I was wondering if any of you could let me know what kind of metrics you use for your backtesting results before you decide to execute a strategy. Things such as Drawdown VS profit, profit factor , number of executions and how far back you look in order to consider your strategy robust enough. I would imagine this has been asked and answered but I was unable to find a thread. Any insight would be appreciated.
Thanks
More...

One of the important things I will check are the trading expectancy, %win, %loss, average net profit per trade. You can read more details here: http://www.stock-trading.me/2010/11...esting-of-stocks-using-ms-excel-the-easy-way/
 
The first thing I look at after statistical significance is % average profit. If it isn't really good, the system gets tossed into the archives. Of course the exact number will be up to the developer as to what constitutes "really good".

This was one of the most valuable pieces of advice that was passed on to me at a key stage of my development, and frankly I sort of ignored it at the time and learned it the hard way anyway. The volume approach just looked too damn appealing at the time for me to heed the advice.

Think of it as a business. Why compete for scraps? If you have big fat profit margins you don't have to worry as much about executions, and you tend to see the margins shrink with enough warning to know your strat is getting popular without it costing you a lot of money.

Frankly I feel I should just not post this here, but then again someone gave this knowledge to me in a directed and no-cost manner and I didn't really heed it then, so I suspect most of you will ignore it or otherwise overlook the significance of such a simple piece of advice.

For the one or two people who need it at this stage in their development, take it and thrive...
 
Quote from iagainsti:

You, sir, are a jackass...
More...

He is that and much, much more. He and some others like him are the real idiots here. They make unjustifiable statements and present themselves as authorities.

Just ignore the idiot. More importantly, don't pay attention to anything he says. He is too frustrated and too big of a loser for his words to have any weight here.
 
Quote from goodgoing:

He is that and much, much more. He and some others like him are the real idiots here. They make unjustifiable statements and present themselves as authorities.

Just ignore the idiot. More importantly, don't pay attention to anything he says. He is too frustrated and too big of a loser for his words to have any weight here.
More...

Aww, it's ok if you don't like me. I did school you pretty bad in another thread (that shall remain nameless for now), so, I can understand the resentment.

Do you really me want to expose your shortcomings all over again here? (don't answer, I think I know the answer).

Here it is again: just like Ninna mentioned, 97-98 presented some challenges for MR systems. This is well documented. Anyone who doesn't research this concept for themselves, and do their homework stands to be caught off guard.

No one is presenting this regime change idea as authoritative. In fact, it may not effect a well designed MR system. The point is one should test it regardless.

You see, that's what successful people do, we stay open to ideas and test the validity for ourselves. (That's friendly advice in case you are too enraged to read for content).
 
You must log in or register to reply here.
Back
Top