Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community. It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
Hey,
I'm currently facing some problems with a new system. The problems is that when I change data range of the historical prices I get different signals. For example if I change starting day 1.1.2010 and compare it with one with starting day 1.1.2011 signals are different for some of the trades. The problem also occurs when i use different symbols and backadjustment types, so that is not the case this time.
Can you help answer these questions from other members on NexusFi?
Sounds like "starting point dependency" to me. If, for example, you are using an exponential moving average (instead of a regular moving average), your results will change depending on where the calculation starts. This is because some calculations (like an exponential ma) calculate using all previous data. The differences might be slight, but just enough to trigger signals at different times.
I was also thinking about that. There is one indicator which are using all available data. How do you handle this kind of situations when placing new orders?
I keep the start date the same for all testing, and then for live trading. In some cases, I am running charts from 5-10 years ago, and trading live, just to keep calculations with a consistent start point.
You could also measure the statistical significance of starting date on you results via a Monte Carlo simulation. THat will give you an indication if you should worry.