I look forward to your proof. Thanks, surf.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an alternative browser.
You should upgrade or use an alternative browser.
Trend Following Research
- Thread starter Trend Following
- Start date
I look forward to your proof. Thanks, surf.
The difficulty I have with statements like "one move predicts a trend" is that "move" isn't well defined.
So the concept of comparing previous day to current day is actually IMO much more mathematically rigorous. But it's not something I would expect to reveal trends. I would expect exactly the opposite - countertrends.
Now, if you started scanning instruments for ones where the past 10-20 days were highly positively correlated with the next day, you might be on to something...
So the concept of comparing previous day to current day is actually IMO much more mathematically rigorous. But it's not something I would expect to reveal trends. I would expect exactly the opposite - countertrends.
Now, if you started scanning instruments for ones where the past 10-20 days were highly positively correlated with the next day, you might be on to something...
Quote from The Big D:
I think we're in general agreement on these points - what your friend told you about the day N vs. N+1 correlation is what I alluded to when I said that many markets are inherently counter-trending on shorter time frames and trending on longer frames. Generally speaking the best detectors (MA crossover, serial correlation, etc) for one vs. the other are not exactly symmetrical either.
Of course, the fact that many markets have positive serial correlation on long time frames and negative correlation on short time frames should suggest a trading system concept with two re-enforcing entry signals. And I know from experience that that class of systems can work very well, although the S&P is not the optimal instrument.
My real point was to demonstrate that there is at least one trend following system that works well. And further, that it detects trends which are not only observed facts in the past, but also predictive of the future.
Yes, thanks for your insight. I can be a little dogmatic at times without fully considering all options and possibilities. However, with this said, I understand, which you may agree, that at lower time frames moving averages have zero testable significance. This would mean that short term or day traders using MA's to trigger entries have no greater edge than random.
Surf
Quote from marketsurfer:
I consulted with one of the smartest market math guys I am friendly with regarding your claims. Although, I know basic stats, I am far from an expert. He advised that over the last 105 days, the correlation of daily SPY with itself the previous day has been negative 10%. The market is negatively auto correlated at lag 1. So whoever made the statement that it only takes one up day to increase odds of success is wrong.
However, MA crossovers can have some significance at the 40 week level and actually begin to work at a little more than 100 days.
I stand corrected with my previous statement.
Surf.
This could be true yet it still be positive expectation to be long, its a matter to how much it rises compared to how much it falls
Quote from marketsurfer:
Yes, thanks for your insight. I can be a little dogmatic at times without fully considering all options and possibilities. However, with this said, I understand, which you may agree, that at lower time frames moving averages have zero testable significance. This would mean that short term or day traders using MA's to trigger entries have no greater edge than random.
Surf
I think, broadly speaking, you're right. I searched for minute-bar trending strategies in quite a few instruments, and found nothing really worth trading. Which makes sense to me - the risk inherent in gunning for stops (either from the market making or market taking side) goes up as the distance in price (and thus also time) to the hypothetical stops increases. So on short time frames I would expect a healthy quantity of false breakouts. But on long time frames generating false breakouts isn't feasible from a risk perspective.
There are two caveats I can see:
1) there are a LOT of instruments in the world. Some may have easy to spot trends on short time frames. I just don't know which.
2) Adding additional sophistication to an entry signal (multiple re-enforcing averages, tick/vol charts etc.) can sometimes separate the chop from the trends. So it IS possible to have a profitable trend following system in markets that do not have a blatant bias towards trending. That said, it's painful and it would make more sense to choose a better game.
Quote from The Big D:
The difficulty I have with statements like "one move predicts a trend" is that "move" isn't well defined.
So the concept of comparing previous day to current day is actually IMO much more mathematically rigorous. But it's not something I would expect to reveal trends. I would expect exactly the opposite - countertrends.
Now, if you started scanning instruments for ones where the past 10-20 days were highly positively correlated with the next day, you might be on to something...
One move doesn't predict a trend.
One move, any move, if defined correctly should detail a fixed point of support and resistance, period.
Quote from The Big D:
Agreed. That definition isn't specific enough to take a chart and mark the "moves" even in retrospect.
I absolutely agree.
Retrospect isn't good enough though, as you well know.
I've defined it and I won't share. There are far smarter individuals in this forum than I am so it shouldn't be too hard for one of those learned individuals to figure it out.
Hey, marketsurfer said that Covel was the "expert" maybe he can put it to pencil.
Got to be worth a few bucks, huh?