[…]he presents is the idea of barbell investing. A barbell investment portfolio is constructed by combining a high percentage (say 80-90%) of very low risk investments with a small percentage (10-20%) of very risky investments. The idea is that the high proportion of the lowest risk investments ensures limited damage to one’s portfolio should all hell break loose while exposure to the riskiest investments allows decent upside. Ride Winners and Cut Losers. Period. For testing purposes, we create 2 samples. The first sample is from 1927 to 1962 and the second sample is from 1963 to 2013. The samples […]
[…]The important part of this calculation is that you use the log values of the daily return. The reason for this is that a 1% up day followed by a 1% down day does not get you a 0% total return. This is what you would get if you simply sum the values. Taking the natural log of 1 plus daily return allows you add the values and get the correct total return. From the average and standard deviation, you can then draw the linear version of the curve from the start to the end of your data, as shown […]
[…]UpClose Length", 2, 2, 100, 1); paramLenRank = Param("PerecentRank Length", 100, 10, 200, 1);function ConnorsRSIa(arr, lenRSI, lenUD, lenROC) { upDays = BarsSince(arr = Ref(arr,-1)); updownDays = IIf(upDays > 0, upDays, IIf(downDays > 0, -downDays, 0)); crsiT = ( PercentRank(ROC(arr,1), lenROC) + RSIa(updownDays,lenUD) + RSIa(arr, lenRSI))/3; return crsiT; }function ConnorsRSI(lenRSI, lenUD, lenROC) { upDays = BarsSince(C = Ref(C,-1)); updownDays = IIf(upDays > 0, upDays, IIf(downDays > 0, -downDays, 0)); crsiT = ( PercentRank(ROC(C,1), lenROC) + RSIa(updownDays,lenUD) + RSI(lenRSI))/3; return crsiT; } crsi = ConnorsRSI(3,2,100);Plot( ConnorsRSIa(C, paramLenRSI,paramLenUD,paramLenRank) , "ConnorsRSI("+paramLenRSI+","+paramLenUD+","+paramLenRank+")" […]
[…]to the strategy. You then let the strategy side compound while keeping your original cash amount. For example, we choose to start with 10% in the strategy and 90% cash. That means our first trade will be allocated $10,000. When the strategy exits and then gets a new signal, the next trade will use total cash minus the original $90,000 of cash. This lets the strategy quickly outgrow the initial allocation. One can see that even at starting with 5%, the portfolio eventually gets to be as much as 87% exposed. At 15% and above, the maximum exposure nearly becomes […]
[…]globe.Included in The Course Approximately two hours of online instructionOne hour of one-on-one access (over email or Skype) to Matt to ask any questions you may haveCode templates that you can easily modify for your own needsAmiBroker test results I found Matt’s CBT Course to be invaluable. Having used Tradestation for many years, I began working with Amibroker about a year ago. Matt’s help was a massive shortcut for me. There are many possible pitfalls when designing and testing systems. Improper coding is certainly one of them. And with Matt’s help, I was able to learn how to code in Amibroker […]
[…]daily data, going back to 1999 is preferred for me because I like using from 2000-2006 for out-of-sample testing. But for free this is great! They also have lots of free non-price data like Twitter and StockTwits Trader Mood and Sentdex Sentiment Analysis. Read more at Quantopian Data. And then there is the fundamental data. This caught my attention. It has Factset Fundamentals data up to until a year ago. Some of this data you must pay for but the prices seem reasonable. Most come with free sample data which makes testing your idea possible to see if it is […]
[…]stock service based on ideas from the article. Tranquil Trades outperform the S&P 500 by 3:1. Get one month free signals with sign […]
[…]to our prior work for details, but in short, we searched for the best canary universe over the in-sample period from Dec 1926 – Dec 1970. We found a two-asset universe consisting of the US Aggregate Bond and Emerging Markets as the optimal canary universe to identify the trend of SPY in the next month. In the following, we will use two Vanguard ETFs — BND and VWO — to represent both assets. What is the intuition for using BND and VWO as a canary universe? One hypothesis is that SPY is sensitive to yields (higher yields leading to lower […]
Continuing from the last post, I will show how using different definitions of passing our out-of-sample test can change our results. How luck can play a role if you use only one strategy to test out-of-sample. How you split your in-sample(IS) and out-of-sample(OOS) can change results. The Strategy I will be using a stock mean reversion strategy with an average hold of three days. Some of my comments may not apply in different situations. Any mention of ConnorsRSI is using the default parameters of (3, 2, 100). The parameters tested below will give 1000 variations. Set up Rules Stock is […]
[…]service can help Save you money Give you confidence in your strategy Set your expectations on potential future returns Sample Report Get Started Now Want to learn more about how I can help you and what the process is? Sign up for a free 30-minute call about your strategy evaluation. The cost of this service is dependent on how extensive you would like the analysis to be, with a starting price is $250. Let me help you stress test your strategy. Contact me to get […]
