Pair Trading Strategy Journal

Quote from total_keops:

If you have the stock data you can use Excel and compute the stdev() on a rolling window of x days. A simple as that.
More...

I was hoping to find data already calculated. I don't have the stock data (there are about 120 stocks) and, yes I could enter the SD formula, but havn't done that before. It seems simpler to just get the SD, Volatility or will Beta also be satisfactory for the purpose?

wb
 
Quote from mlsignups:

I downloaded the package. I first tried to put all stocks in by sector, ran the backtester and saved all results with correlation > 70% but my list got so long I crashed the program.

Then I cleaned out the whole database and put in one by one the industry list(s) they supplied for each industry (i skipped financials). Then I once again have been running the backtester and this time have only been grabbing those that come up with correlation > 85%.

I figured once all the pairs got in the main watch list I would try to narrow them down some more form the main list.

If you don't mind maybe you can give me a little guidance. As I mentioned I run the back tester by industry then just grab all pairs with a correlation > 85%. You have far less pairs so...When you are at the back tester level do you analyze them in more detail before putting onto the list?

You also mentioned that you never put the same stock in twice, but if you have one stock that correlates with 3 others very well how do you choose which one to put it onto the list with? My thinking is put them all on the list and then look at the charts when a signal comes up to choose - maybe at a given time one stock will be correlating with a different one better so why not put them all on the list?

Thanks for the journal and any advice you can supply.
More...

Any more than 200 pairs I think is too much, each pair gives roughly 10 signals per year, so 200 unique pairs gives you a possible 2000 trades per year which is plenty. So I would refine your lists by simply ranking them by correlation, just keep the top 100 or 200 correlated pairs, I prefer to have unique pairs because then you get more tradeable signals per pair, in the backtester I look for ratio charts in wide trading range before I add the pair to my watchlist. There really isn't any hard & fast rules to what type of pairs you should add, its up to the trader to find what their comfort is, for eg... some traders may be very knowledgeable of the restaurant industry and therefore may only stick to trading restaurant pairs because they know the fundamentals well, know how the stocks trade, etc......I like trading a diversified portfolio of different pairs from different industries.
 
Quote from Etrade18:

Jonny,


With your SIM trade at what price did you get short? Was it the 4.60 MOC print (like you said u usually get the trades at the MOC print) t
More...

No I don't think I got that trade on the print, was shortly before the close.
 
Quote from waltbx:

The trading stragegy we have been examining is mean reversion pair trading, dollar neutral. Something I'm beginning to look at, using the data from Jonny's spread sheet is Unilateral Pairs Trading. One assumes that of the two stocks in the pair, one is the cause of the divergence from the mean. If that one can be identified, it can be traded and the other one not. (Yes, that means loosing the protection found with trading the other stock of the pair, the hedge). It is suggested that a way to identify the "wayward" stock is to identify the one with the highest volatility.

I want to test this strategy. I need to know where to find historic volatilities for the single stock of interest (not the pair, which PT gives us). I'll enter that into Jonny's spread sheet and see if there is any correlation between the volatility and profit in each pair Jonny traded since August 2008.

Any suggestion on easily finding historic volatilities? Are there lists, or a charting site where I can simply enter the symbol, date, and get my stat? I've looked without success.

Jonny, thanks for sharing that spread sheet. It's been a terrific learning tool for me. I've analyzed almost every trade to learn how to identify winners from loosers. Still learning.

Walt B
More...

Yes Ive heard of this theory aswell, the higher volatile stock producing the most returns, however my issue is that just because one stock may have a daily volatility of 3% and another stock has 2%, it doesn't mean that the move that the signal occurs on is from the higher volatile stock, the 2% stock may have moved more in the short term and produced the divergence. and if one stock has significantly different volatility to the other stock, I would say this isn't a good pair to trade as they aren't very similar, plus trading naked is way more risky as you suggest, therefore your returns become correlated to the market and you can't use as much leverage. yeah I would suggest excel spreadsheet aswell to compute volatility if you want to investigate this, I would interested in seeing the results. Yes it is a good idea to go over the winning and losing trades to try and look for a repeatable pattern, something i do with the losses, but at the end of the day a lot of it is random, the next trade result really is random, whats important is an edge over a number of trades.
 
Over a period of years, are pair trades more successful during periods of higher volatility, and less so during periods of lower volatility.

Walt B
 
Hi Johnny,

Have you noticed that sometimes the ratio appears to be clearly away from the average line and yet no signals are generated?

Also, have you looked at all at high or low RSI as a condition when a signal is generated? Seems like some good moves come from that but often the outliers appear associated with news.

I've had minor luck so far trying this but I feel like I'm just blindly following the signals without any real confirmation from what I'm seeing. You still having good luck?

Thanks.
 
Quote from waltbx:

Over a period of years, are pair trades more successful during periods of higher volatility, and less so during periods of lower volatility.

Walt B
More...

generally speaking yes, buts that's a subjective question because in periods of higher volatility the risk and reward both increase and you adjust your size accordingly, just as you increase your size in periods of low volatility, but yes higher volatile environments can present unique opportunities. so long as pairs diverge from their mean there will always be a trade to take.
 
To calculate the profit from the change in ratios I think this formula will work.

The (% profit) = (% change in the ratios)/2

The following is from my spread sheet on recent trades:
Example 1: The ratio moves up 9.3%, the profit is 4.7%
Example 2: The ratio moves up 23%, the profit is 12.1%
Example 3: The ratio moves up 13.2%, the profit is 6.9%

Try it with some figures of your own.

Walt B

Quote from jonnysharp:

I wish it were this simple, and unless I'm misunderstanding something here, this won't work. It is an increase of 18.18% in the ratio, but the profit won't fall out by multiplying that by one side of the leg.

Am I missing something?

WB
--------------------------------------------------------------------------------



Let me give you an example;

Long $10k ABC @ 100
Short $10k XYZ @ 181
Ratio = 0.55

Sold ABC @ 118
Covered XYZ @ 181
Ratio = 0.65

Profit on ABC = 18% ($1800)
Profit on XYZ = 0% ($0)

0.65 / 0.55 = 1.1818
More...
 
Quote from LazyLightnin:

Hi Johnny,

Have you noticed that sometimes the ratio appears to be clearly away from the average line and yet no signals are generated?

Also, have you looked at all at high or low RSI as a condition when a signal is generated? Seems like some good moves come from that but often the outliers appear associated with news.

I've had minor luck so far trying this but I feel like I'm just blindly following the signals without any real confirmation from what I'm seeing. You still having good luck?

Thanks.
More...

Yes Ive noticed this, probably something to do with increased volatility. Yes I look at the RSI chart with each signal, i like divergences also you can tell by looking at the RSI chart whether a pair is good to trade or not, i like a chart that looks like a heartbeat graph, regular and consistent oscillations around a average. You gotta stick at it, its not about luck, rather consistent application of a method with a edge, too many traders judge their results after too little trades, treat your trading like a business, losses are business costs and wins are revenue, so long as your revenue exceeds your costs at the end of each quarter you have a profitable business.
 
You must log in or register to reply here.
Back
Top