Statistical Analysis of Intraday Data - Any worthwhile resources?

schizo said:
I hear ya. No, I didn't expect you to show your hands.

I'm also interested in including some type of stats into my current strategy but I question whether you can formulate a "pure" stat without any ties to price action. For example, "buy when price crossed above MA(20)" or "buy when close is above close of yesterday" are PA-based. But "buy when the mean or median of 20-period is 2% above close of x-days ago" might not be. I'm mostly interested in formulating volatility/momentum into the equation. Any suggestion for this noob?
More...

I think you would benefit a lot from the chapter in Brett Steenbarger's The Daily Trading Coach where he talks about conducting historical analysis using daily data. It's fairly simple, but it is a good starting point. His blog also contains a lot of stuff on this.

However, for me, I'd say a strategy such as that would be too crude and not accurate enough to utilize in my trading. If something works only 50-60% of the time, why bother? Might as well flip a coin, no?

Last week on S&P, I actually discovered a pattern, admittedly somewhat rough, that repeated itself similarly the last 9 times I checked. Sadly, last week was the exception of the norm. That would make it 9 out of 10 times. Still pretty good, IMO, but I was disappointed to see it not play out as I had hoped/predicted. Adding more parameters though, I'm thinking perhaps I could have predicted the deviation.

That's where I'm still puzzled. What stuff is relevant and what is not. And are some stuff relevant to include just some of the time?

It's not easy, but I'm a believer. :)

PS: I think it's amazing to see how many people who can't even tell you what the average N-day RANGE is in the instrument they trade. Knowing this alone will give you at least some expectation of what will happen on any given day.
 
vicirek said:
There are numerous books on the topic. Just search for statistical learning or statistical pattern recognition or (nonlinear) time series and you will find multiple books (Amazon) and web pages. Unfortunately most of them are not in human readable form due to the fact that academia tends to make relatively simple things complicated for outsiders.

I found that some of the books that are written for R or Python users tend to be more reader friendly. I guess machine learning also includes statistical learning since it is general term and you can include it in your searches as well. For basics in machine learning I would suggest Machine Learning in Action.

There are relatively cheap ebooks on Amazon and elsewhere for few $ like Introductory R: A beginner's guide, 100 statistical tests in R and others; just to give you some ideas. There are also books addressing financial markets directly like Python for Finance (there are others like this for R, #F, Haskell, C++) and some of them include statistical concepts applied to markets. I am not recommending all of them since they may not suit your needs. Some are not that good except for few more or less useful chapters or they might be too difficult despite the fact that those were written for people without advanced degree in math or statistics.

I think just searching and skimming through table of contents and few pages available for preview gives some idea if it is useful and as a bonus it can narrow your search criteria.

Unfortunately I cannot recommend single best resource and I am not an expert in statistics nor I apply it directly to market data but rather use it as a set of utility tools.
More...

Thanks, man. Those are good suggestions. I'll look into them.

My workload is currently killing me, but I'm hoping to learn programming on my own in time.
 
Howard said:
Hello traders.

I'm curious if there are any resources, either online or in books, where I could perhaps get some further inspiration or ideas on the topic?
More...

I have been using statistical analysis to develop my trading systems for about 3 years, with increasing success as I learned from my mistakes.

I have a webinar video on the NinjaTrader partners channel, from March 2015 (I think), in which I did provide a lot of information re. my approach to it. Unfortunately, on top of my ESL accent, the audio is really bad, which makes going through the entire recording a big annoyance, but if you can do it, I guarantee you'll get access to a lot of valuable information.

As for your post mentioning a "pattern" with a sample size of 10, no matter the win%, consider that as noise.

(the topic of delineating between noise looking as a recurring pattern, and a statistically valid recurring pattern, is the KEY issue in what you are getting into - sample size is only one part of what I use)
 
dom993 said:
I have a webinar video on the NinjaTrader partners channel, from March 2015 (I think), in which I did provide a lot of information re. my approach to it. Unfortunately, on top of my ESL accent, the audio is really bad, which makes going through the entire recording a big annoyance, but if you can do it, I guarantee you'll get access to a lot of valuable information.
More...

I would be very interested in looking at this. Thanks! Where can I find this? Would this be their Youtube channel?

As for your post mentioning a "pattern" with a sample size of 10, no matter the win%, consider that as noise.
More...

Perhaps, but I'm not sure I agree. I tend to weigh the most recent past the most for various reasons, hence why I didn't go further back. I had to go back a whole year to find 10 similar occurences.

But I'll take it into consideration. I'm careful to jump to conclusions. :)
 
Maybe I'm paranoid, but I've written out two posts today that I deleted before posting since I'm feeling very secretive about my approach. :)

I'm going to see if I can watch that video now.

I put together another piece of the puzzle earlier today. A lot of my questions have been answered, but typically, new ones arises when old ones are answered. :)
 
Maybe this makes me an asshole, but that video seems to be a sales pitch?

I'm also reasoning that if someone has a really, really good system, they would never fully disclose it in public or sell it. Instead, they would trade it themselves to become filthy rich. With a really good system, you should be able to scale up fairly quickly even starting with a small size account.

Or am I missing something?

I would never sell my own system if it was a good one.
 
Howard said:
Maybe this makes me an asshole, but that video seems to be a sales pitch?

I'm also reasoning that if someone has a really, really good system, they would never fully disclose it in public or sell it. Instead, they would trade it themselves to become filthy rich. With a really good system, you should be able to scale up fairly quickly even starting with a small size account.

Or am I missing something?

I would never sell my own system if it was a good one.
More...

Yes it does (make you an asshole) - and yes it is (a sales pitch).

Your reasoning is wrong. I don't have unlimited capital, or even a capital-base large enough to make a living only from trading. I have chosen to make trading my primary activity, and I still have bills to pay, every month, regardless of each month's net P&L. So offering my systems for lease is a good way to increase the return on my R&D efforts.

You don't realize how much R&D is needed for a production-type trading system, this is out of reach for 99% of people interested in extracting money from the markets, and it is primarily for these people that I am offering my systems for lease (that said, I have clients who trade their home-grown systems + mine).

You are wrong thinking I am *fully* disclosing everything - but it is true that I am disclosing enough for anyone with enough time & skills to get going doing similar things. This was my intent in pointing you towards that video, too bad for you if you can't make any more from it than this.
 
You must log in or register to reply here.
Back
Top