Contributor Since 2010
I often use linear regression channels to help in my assessment of market trends and I thought I might detail some methods so that other investors can benefit. In the current somewhat overheated market these techniques are invaluable in assessing reasonable entry points as stocks move higher and higher.
What is a linear regression? On a typical stock chart we have price represented over time as the main characteristics with a ‘Y’ axis (price) and an ‘X’ axis (time). A linear regression analyzes the relationship between these 2 variables ‘X’ and ‘Y’ and attempts to find the best straight-line path through the data points. The goal of the regression analysis is to find the best line that comes closest to predicting ‘Y’ (price) from ‘X’ (time). The way I use it is to build a trend channel based upon a linear regression of recent price action in an attempt to determine what a reasonable entry point might be.
Let’s take a look at a quick example using the SP-500 index itself. What we are going do first is draw a linear regression channel using a Raff regression channel tool built-in to TC2000, my favorite charting software. Developed by Gilbert Raff, the Raff Regression Channel is a linear regression with evenly spaced trend-lines above and below. The width of the channel is based on the high or low that is the furthest from the linear regression. The chart below shows the SP-500 with a Raff regression channel drawn from the December 2010 low to the close on 3/3/11.
The way I would interpret this is as follows:
1) The midpoint of the regression channel sits roughly at 1340. A break above this level would indicate to me that the index would more than likely try to test resistance at the upper channel band, which currently sits just under 1400. A failure to break above the mid-channel line might indicate that a test of the lower channel boundary, currently around 1300 is in the cards.
2) Using the levels defined above I might decide to increase or decrease my market exposure as the situation dictates.
The Raff regression channel technique can also be used with individual stocks to help pick reasonable entry points, especially where a stock has risen very rapidly. Let’s take a look at a known high flier in the tech space: NFLX (Netflix). Here is the chart:
The basic technique is to identify the beginning of the latest trend (up or down) that you wish to analyze and draw a set of regression channels from that point forward. We are going to use the correction that finished in July 2010, in which the stock declined about 22% in a little more than a month. You can see the action has been choppy but the essence of the analysis is the same. The stock has fallen below the midpoint channel line and looks like it may test the lower channel. If you were fundamentally bullish the place to add to your positions would be after a successful test of the lower channel line or a break above the mid-channel line. If a stock breaks out above the upper channel line with volume that is always a very bullish signal and may indicate an acceleration of the trend.
I hope this short introduction to regression channel analysis helps you in making better day to day investing and trading decisions. In the future I hope to expand upon this technique and demonstrate how I use consolidations after a big run-up to gauge an entry point into a high flier. Thanks for reading.
Disclosure: I am long SPY.