Using Recent Weeks to Predict Stocks In 2012

${Html.ActionLink("My MarketWatch", "index", new { controller = "composite", area = "section", page = "my" })} | !{Html.ActionLink("Sign out", "LogOff", new { area = "User", controller = "Account" }, new { id = "signOutLink" })}

Welcome, ${UserDisplayName}

Log in

Become a MarketWatch member today

Mark Hulbert Archives | Email alerts

Jan. 17, 2012, 12:01 a.m. EST

By Mark Hulbert, MarketWatch

CHAPEL HILL, N.C. (MarketWatch) "” Hope springs eternal"”especially when it comes to the stock market and January.

Just take my column a week ago, in which I argued that the stock market's direction for the rest of this year had nothing to do with its direction over the first five trading days of January.

Lots of you refused to accept this conclusion, arguing that I would have found the indicator to have a great track record if only I had properly coupled it with others.

Let's see.

For starters, let's review what I reported for the "first five days of January."

I found that, over the last century, the stock market rose 65% of the time from the end of January's first week through the end of the year. Those odds of an "up" year rose by only 4 percentage points when the market rose over that first week, and fell by only 7 percentage points when the market declined over the first five trading days of the year.

Given the variability of the year-by-year results, even these modest differences were not significant at the 95% confidence level that statisticians often use to determine that a pattern is more than just a fluke. ( Read Jan 11. column on the "first five days of January" indicator. )

One of the approaches that a number of you suggested was coupling the "first five days of January" indicator with the so-called "Santa Claus Rally," which encompasses the last five trading sessions of December. What are the odds of an "up" year when the market rises in both periods"”as indeed the stock market did at the end of last year and the beginning of this?

The relevant data are presented below, based on the Dow Jones Industrial Average /quotes/zigman/627449 DJIA -0.39%   back to 1896, when it was created..

Ironically, the odds of an "up" year now appear to be higher if the Dow falls in both periods than if it rises. And, strangely, the odds go down if the Dow rises in just one, but not both, of the periods.

Before you spend any energies trying to come up with a plausible story for why these results make sense, let me hasten to say that the differences between these percentages are not statistically significant at the 95% confidence level. So they probably aren't even real.

To be sure, this particular combination of two indicators is not the only one that you have presented to me, and I haven't analyzed every one of them. It's entirely possible that one of them would show apparent promise.

But even if that were to turn out to be the case, this still doesn't mean you should alter your portfolios because of it. That's because, as I study more and more indicators and combinations of indicators, the odds of a "false positive" grow as well.

Imagine that I have tested one hundred different indicators and combinations of indicators. At the 95% confidence level, we can expect that five of them will appear to be significant when in fact they are not.

Sounds depressing, I know.

But hope is not a strategy.

The stock market will rise between now and the end of 2012 if investors conclude that publicly-traded corporations collectively will be even more profitable in the future than they currently expect them to be. Whether or not that turns out to be the case will have nothing to do with how the stock market performed in the weeks before and after the beginning of this year.

Click here to learn more about the Hulbert Financial Digest.

Mark Hulbert is the founder of Hulbert Financial Digest in Annandale, Va. He has been tracking the advice of more than 160 financial newsletters since 1980.

China stocks rebound on GDP data, lead Asia

CEO of the Year: Cloud, Fire lifted Amazon's Bezos

Using recent weeks to predict rest of 2012

How Dell is reinventing Dell Inc.

China growth cools, easing seen as likely

Using recent weeks to predict rest of 2012

Save the World: Join our new investing mission

Till debt do us apart

Euro's "?funding' role far from assured

Asia Week Ahead: China's Bank Reserves In Focus

The Fed: Waiting Too Long To Raise Rates?

Mark Hulbert: Don't Bank On Early-January Effect

Europe's Week Ahead: Central Banks In Focus

Mark Hulbert is editor of the Hulbert Financial Digest, which since 1980 has been tracking the performance of hundreds of investment advisors. The HFD... Expand

Mark Hulbert is editor of the Hulbert Financial Digest, which since 1980 has been tracking the performance of hundreds of investment advisors. The HFD became a service of MarketWatch in April 2002. In addition to being a Senior Columnist for MarketWatch, Hulbert writes a monthly column for Barron's.com and a column on investment strategies for the Journal of the American Association of Individual Investors. A frequent guest on television and radio shows, you may have seen Hulbert on CNBC, Wall Street Week, or ABC's World News This Morning. Most recently, Dow Jones and MarketWatch launched a new weekly newsletter based on Hulbert's research, entitled Hulbert on Markets: What's Working Now. Collapse

Paul B. Farrell

Behavioral Economics

Save the Word: Join a new investing mission

Mark Hulbert

On the Markets

Using recent weeks to predict rest of 2012

Ruth Mantell

On the Job

Stressed at work? How to find job satisfaction

Kristen Gerencher

Read Full Article »




Related Articles

Market Overview
Search Stock Quotes