BackTesting vs WalkForward

Quote from walterjennings:
Wouldn't any system using any element of knowledge outside the current state of the market (ie. knowledge of the past), be considered to be using 'lagging indicators' in a sense, since past knowledge can not exactly predict the future? I'm curious how you can design a system which only uses current market state (outside of stat arb, but even then you will want to model past arb opportunities). Even if you had current price and price triggers to trade, those price triggers will have some element of knowledge of the past (range, offsets, direction).
More...

Certainly it would, but when I say lagging indicators I refer to those MACD, RSI etc. that all has a reputation of the holy grail in newbie-eyes.

One can say that price and volume is indicators, sure volume is an indicator as it indicates the volume, but lagging indicators is magic calculus which averages over a period of a type, often time.:p
 
Quote from januson:
One can say that price and volume is indicators, sure volume is an indicator as it indicates the volume, but lagging indicators is magic calculus which averages over a period of a type, often time.:p [/B]
More...

Price and Volume are not indicators, they are used in the calculation of indicators.

Investopedia explains Indicator
In the context of technical analysis, an indicator is a mathematical calculation based on a securities price and/or volume. The result is used to predict future prices. Common technical analysis indicators are the moving average convergence-divergence (MACD) indicator and the relative strength index (RSI).

In an economic context, an indicator could be a measure such as the unemployment rate, which can be used to predict future economic trends. Common general economic indicators are the unemployment rate, new housing starts and the consumer price index (CPI).

http://www.investopedia.com/terms/i/indicator.asp
 
Quote from asynchronous:

Price and Volume are not indicators, they are used in the calculation of indicators.

Investopedia explains Indicator
In the context of technical analysis, an indicator is a mathematical calculation based on a securities price and/or volume. The result is used to predict future prices. Common technical analysis indicators are the moving average convergence-divergence (MACD) indicator and the relative strength index (RSI).

In an economic context, an indicator could be a measure such as the unemployment rate, which can be used to predict future economic trends. Common general economic indicators are the unemployment rate, new housing starts and the consumer price index (CPI).

http://www.investopedia.com/terms/i/indicator.asp
More...

I am aware of the concept. An indicator is something that indicates something... Accumulating volume is indicating total volume over some period of type.

As soon as a person starts to think about building a strategy he will always use indicators, my post was just to say "avoid those lagging ones" Put in another way... as soon one starts to look over some period of type then the indicator is lagging.
I don't believe that there exists any strategies that doesn't use indicators of some sort lagging or non-lagging - and that was my point :)
A price or volume has absolutely no value if it cannot be compared with similar values. And as soon one starts to do that, the price is indicating something - Investopedia or Not!!:cool:
 
Quote from januson:

I am aware of the concept. An indicator is something that indicates something... Accumulating volume is indicating total volume over some period of type.

As soon as a person starts to think about building a strategy he will always use indicators, my post was just to say "avoid those lagging ones" Put in another way... as soon one starts to look over some period of type then the indicator is lagging.
I don't believe that there exists any strategies that doesn't use indicators of some sort lagging or non-lagging - and that was my point :)
A price or volume has absolutely no value if it cannot be compared with similar values. And as soon one starts to do that, the price is indicating something - Investopedia or Not!!:cool:
More...

Januson,...You are quite right!

However, I use leading and lagging indicators quite successfully...heres how...

In the past, I used them to generate my entry signal - directly,... my results were marginal.

I now use them to qualify the possibility of entering the trade.
After I get the go ahead (from my indicators), I look for things like pullbacks, I analyze risk and I determine momentum.

Once All of the planets align,...I enter the trade.

I never use indicators to exit the trade - ever (with the exception of the Parabolic SAR (OK, I just contradicted myself (so what))).

This works best for me.

<><><>

Also there are strategies that don't use TA at all. One I hope to work on shortly is the design of a News Scrubber - rank key words and assign them to a fear/greed index.
 
Quote from januson:

Very simple, no need to buy a book for such.

Backtesting is based at curvefitting over a period, for instance curvefitting/ optimizing the last year looking for 30min trades. Then your optimixer will calculate the gain/ loss and you will clap your hands and look very happy sitting there imagining yourself as a millionaire.

Forward testing, you don't have anything to start with... as the data arrives you will build a strategy, refining it over time and then let the system run forward.

Backtesting really sucks bigtime, forwardtesting is much more realistic, though you can easily "cheat" performing forwardtesting in the same manner as backtesting optimizing the whole period.

Backtesting can of course easily be treated as forwardtesting only curvefitting a small period. But people need some distinction between the concepts, hence the naming :)
More...

It sounds like you are assuming the back tester will be stupid enough to use the same time periods for the learning phase that he uses for the testing phase. Assuming that the back tester has at least the brains of an oyster, he will not do this, but will instead use different time periods for those two purposes. That being the case, how is forward testing fundamentally different from back testing?
 
You must log in or register to reply here.
Back
Top