Why investors shouldn't follow their gut

(MoneyWatch) Many investors make the mistake of looking at recent performance when making investing decisions. Given the recent performance of some asset classes, investors could be in danger of making poor investment strategy decisions.

To illustrate the problem, the following is an example offered by the late psychologist Amos Tversky. Imagine that two bags are filled with the same number of poker chips. Bag A has two-thirds chips that are white and one third that are red. In bag B the proportions are reversed. From bag A, you withdraw five chips, four of which turn out to be red. From bag B, you withdraw 30 chips, 20 turn out to be red. Which bag would you guess has the most red chips?

If you're like most people, you would probably guess bag A, since 80 percent of the chips you withdrew were red, versus just 67 percent from bag B. However, you're more likely to be right if you chose bag B. The reason is that because the sample size from bag B is much larger, you have more confidence in the result.

This mistake is one often made by investors: They use small sample sizes to set their investment strategies or to choose individual investments, when they would be better off looking at longer time periods. Consider the following annualized returns for various indexes over the past three years.*

Think of this period as bag A, from which you were only able to draw a small sample. Large-cap growth beat small-cap value, and large-cap value brought up the rear by a considerable margin. However, consider the returns of the same asset classes for the longest period we have available, which is 1927 through 2012.

The long-term data shows that small-cap value has actually been the top performer, and by a significant margin. Large-cap value was actually the second best performer, not the laggard it appeared to be from the past three years. These type periods create the problem often referred to as recency -- putting too much weight on the current market environment when making decisions.

Investors subject to recency, ignoring the much larger data set available to them, are making the same mistake as those who chose bag A on the basis of a small sample. Basing investment decisions on small samples can lead to costly outcomes, particularly if a small and probably recent data series causes you to abandon a well-designed investment strategy.

As my colleague and co-author Jared Kizer pointed out in his blog, investors don't seem to understand just how much data you need to be confident in its accuracy. Instead, we have a tendency to hope we have enough, then make our decisions.

In some areas of life, this may be the best we can hope for. Investing isn't one of those areas. Always be wary of anyone who is recommending investments or strategies based on anything less than all the evidence available.

* U.S. large-cap growth represented by the Fama/French US Large Growth Index (ex utilities). U.S. large-cap value represented by the Fama/French US Large Value Index (ex utilities). U.S. small-cap growth represented by the Fama/French US Small Growth Index (ex utilities). U.S. small-cap value represented by the Fama/French US Small Value Index (ex utilities).