Category Archives for "Research"
A reader recently asked how to do equity curve correlation. For detailed information on correlation you can read Correlation and dependence or for simpler explanation read Correlation at Math is Fun. For steps on how to do this in Excel, which is where of course I did it, read Correlation at Excel Easy. I will cover here how one can correlation analysis between equity curves.
My previous post The Health of Stock Mean Reversion: Dead, Dying or Doing Just Fine generated good reader’s suggestions on other ways to check on mean reversion health. Let us see what these tests tell us.
Wow, what a tough week. But how unusual has this move been? I had a couple of readers send in some ideas to test. These are always fun tests to do when the market goes crazy but usually they don’t provide enough data points to act upon.
My second post on this blog was a look at mean reversion, Is mean reversion dead? Given I am using a new data provider(Premium Data), it has been almost two years since that post and there have been other articles on this recently, I figured it was time to check again. The research will focus on Russell 1000 stocks since 1995. The test is back to 1995 covers 3 bull markets and 2 bear markets.
We hear it all the time. “You must use stops.” And most of us use them. But do you know how they change your strategy results? Are they improving your results by giving you higher CAR or lower maximum drawdown? Recently I was speaking with a reader about this topic and he insisted that it you had to have stops to trade. Well, does one?
A popular topic lately has been “Smart beta” ETFs. What is smart beta? It is using different ways to weight an index and the ETF that tracks it. For example, the S&P500 index is a capitalization weighted index. Bigger companies have a larger portion of the index. If you look at the SPY, Apple which is the largest company, accounts for 4% of the index (https://www.spdrs.com/product/fund.seam?ticker=spy). Other ways one can weight an index are equal weight, by volatility, by fundamental measures, by technical measures and so on. Why would you do this? To beat the returns of the S&P500 index . But are these other ways better?
David Weilmuenster is today’s guest author. David and I worked together at Connors Research for eight years and is one great researcher and AmiBroker programmer.
Brochures for professionally managed investments and academic white papers on long term investing almost always praise the benefits of regularly re-balancing a portfolio. The benefits can arise from the interaction, or correlation, of periodic returns among the constituent assets in a portfolio. As the correlations among constituent assets decrease, the long term returns of the overall portfolio generally will increase with regular re-balancing. This has become known as “the only free lunch in investing”, although it does not work out that way in all situations.
How strong is this market? The SP-500 index had closed above its five day moving average for 29 days and on Friday it finally closed below it. The last day it closed under the five day moving average was on October 16, 2014. This is the longest streak since 1963 (that is as far back as my data goes). The old record was 26 days in 1986. The previous best streak in the last decade was 19, which has been crushed. The index has not had a short-term pullback in the last month which is tough for a short-term mean reversion trader.
The question that always follows is what happens when the streak is broken. We will see what happens if one enters at the close the day the streak is broken and then exit 5 days, 1 month, 3 months and 6 months later.
This post will cover in detail two different ways of doing Monte Carlo analysis and the code needed to it in AmiBroker. A reader recently sent me this article, Monte Carlo Analysis For Trading Systems. The article covers three methods of Monte Carlo analysis. One of which I had never thought about and I had to slap my head on how simple it was.
About once a month, someone asks how important it is to have dividend adjusted data. Or someone will comment they do not want to use Premium Data because they do not adjust for dividends (it does but it is not enabled by default). My answer has been “without dividend adjusted data, your results may be understated.” It has always bothered me that I could not give a better answer. In my post, “How much does not having survivorship free data change test results?” I covered other data issues but not this one. Since Premium Data makes it easy to have two databases, one with the dividend adjustments and one without, it was time to run tests and determine how much of a difference it makes.