Happy New Year. With this being the first issue of 2007, we're going to do a little myth-busting today - alerting you to one dangerous indicator that just doesn't indicate what it's supposed to.
It's human nature to reduce complex systems to simple terms. We're often willing to believe cause-and-effect explanations that really don't make logical sense.
One good example is Groundhog Day. If Punxsutawney Phil sees his shadow on February 2, there will be six more weeks of winter weather. We all know how accurate Phil is...
Subscribe to MoneyWeek
Subscribe to MoneyWeek today and get your first six magazine issues absolutely FREE
As 2007 gets underway, the stock indicator getting the most press this week is the 'First Five Days' gauge. But be warned... it's a lot of hype, and it just doesn't work.
First five days indicator: popular, but useless
The 'First Five Days' indicator was popularized by Yale Hirsch's Stock Trader's Almanac. It holds that the 'First Five Days' of January predicts the direction of the market for the remainder of the year.
As proof of the indicator's effectiveness, its proponents trace the indicator's performance back over 55 years, and state that of 35 'First Five Days' periods that finished up, the stock market subsequently finished up in 30 of those years - an impressive 85% win rate for the predictor.
Consequently, venerable sources such as The New York Times, U.S. News & World Report, CNN and Money Magazine have quoted the indicator.
The problem is: It's a useless indicator, based on shaky logic and even shakier statistics. And even worse, it's potentially dangerous to your wealth.
First five days: ignore this investment myth
Let me be blunt: The 'First Five Days' indicator is the lowest form of analysis. It's the opposite of cause-and-effect. As you're about to see, it's the kind of analysis that looks for any cause to tie to an end effect, regardless of logic, and statistical support. It's really no more valid or useful than predicting the stock market based on Super Bowl winners or groundhog shadows. Here are three reasons why:
1. The Logic Is Arbitrary: The raw numbers for this indicator show that the market has gone down during the first five days of January 20 times over the past 55 years. In those 20 occurrences, the market finished the year up 10 times and down 10 times.
Looking at the data, the authors conclude that the indicator has 'been right' 30 out of 35 times if the market begins the year on the up. But wait... this means that the indicator has no predictive value if it starts out to the downside. This 'working in one direction, but not the other' is too arbitrary for me - and is a classic example of where if the numbers don't fit the hypothesis, then you change the hypothesis to fit the data. This is 'curve-fitting' mentality. Do you want to risk your money based on that logic?
2. The Triggering Event Is Not Statistically Significant: This indicator states that all you need to trigger a yearlong market prediction is any move for five days. This means that trivial moves in the market could shape your outlook for the coming year.
But suppose that after the first five trading days, the market was up only one-quarter of a point. This would still trigger the indicator's prediction for an up year. And the problem with having a move of any magnitude trigger an indicator is that a tiny move like this doesn't tell us anything about what the market is doing. A small move either up or down is just random - part of the background 'noise' of the market.
So how do we decide what is meaningful and what is just background noise?
One measure that many analysts use is the average volatility of a price movement. Long-time readers know that I use the Average True Range (ATR) of price as a measure of volatility. In simple terms, the ATR measures the average size of the daily range (the high minus the low), while accounting for gaps between bars.
If we look at the ATR for a five-day move, we'd want our trigger to move up or down by at least half of the average. Anything less would almost have to be considered random.
With that in mind, your industrious editor dug deep into the details of the 'First Five Days' indicator's raw data. I calculated the S&P 500 index's ATR for the last 20 years and checked to see how many of the 'First Five Days' trigger signals could be considered more than random. The answer: Only 4!
3. The Sample Population Is Too Small: When we eliminate the trigger signals that are mere noise, we now only have 12 to 15 triggers of the indicator over the last 55 years. This is not a statistically significant sample to base any predictions on, and this indicator is uncovered as just some simplistic curve-fitting that doesn't mean a thing for traders and investors.
There is plenty of other good analysis for you to use to help guide your trading and investing decisions. So it makes a lot of sense to throw out overly simplistic, statistically meaningless ones like the 'First Five Days' indicator.
And even though the indicator worked last year, don't fall into the trap of assigning an excessive amount of meaning to the most recent data points. By all means use it for cocktail party discussions, but don't waste any money trying to use it to help you make sense of the markets.
By D.R. Barton Jr., Quantitative Analyst, Mt. Vernon Research for the Smart Options Report, www.smartoptionsreport.com
Should your business invest in a VoIP phone service?
Here's what you need to know about VOIP (voice over IP) services before landlines go digital in 2025.
By David Prosser Published
M&S is back in fashion: but how long can this success last?
M&S has exceeded expectations in the past few years, but can it keep up the momentum?
By Rupert Hargreaves Published