TRADING SYSTEMS

Across Time And Tradables

Trading Trends With The Bollinger Bands Z-Test

by Jacinta Chan



 
Standard deviation bands are helpful in determining trends. Here, the author develops a trading system based on this idea that yields high returns with low, controlled risk.

The set of trading techniques that I will present here uses standard deviation bands to determine trends and help develop a trading system that yields high returns at low, controlled risk. The name for this trading system, BBZ, is an acronym derived from "Bollinger Bands" and the "z-score," based on a Working Money article published in  October 2002 by Veronique Valcu. In "Z-Score Indicator," Valcu related z-scores to Bollinger Bands. Intrigued by the article and to continue that discussion, I wanted to take a closer look at that relationship and introduce the Bollinger Bands z-test (BBZ).

RECAP

The z-score (Z) measures the difference (direction) between the closing price (C) from the mean (n-period moving average) given the n-period standard deviation(s). Thus, the formula becomes:

Positive or negative values show that the closing price (C) is above (C>µ) or below (C<µ) the mean, respectively.

The properties that interest traders are return and risk. In finance, average depicts expected return and standard deviation depicts expected risk. In statistics, we can define range trading as prices that are observed within the expected one (1) standard deviation band. We define trend trading as prices that are observed above +1 standard deviation band (for uptrends) and below -1 standard deviation band (for downtrends).

This article will show how to design and develop this trading system. It outlines the research, why the z-score indicator is used, the tests, and the results.

DESIGNING THE SYSTEM

Step 1: Data Analysis
Perform a data analysis on the price series. The most basic statistical tool is the mean and standard deviation of returns. This will give you an idea of the prevailing trend; a positive mean for most days shows an uptrend, and a negative mean for most days shows a downtrend. You can also determine the volatility of returns.

 
...Continued in the March issue of Technical Analysis of STOCKS & COMMODITIES


Excerpted from an article originally published in the March 2006 issue of Technical Analysis of STOCKS & COMMODITIES magazine. All rights reserved. © Copyright 2006, Technical Analysis, Inc.



Return to March 2006 Contents