(MONEY Magazine) – A controversial technique called back testing is being used increasingly in ads to show how new investing strategies would have performed historically--if somebody had thought of them.

For instance, recent ads for Merrill Lynch show that its Defined Asset Funds Select S&P Industrial Portfolio, which invests in the highest-yielding stocks in the Dow, would have beat the S&P 500 index by 60% from 1977 to 1996. Similarly, Standard & Poor's ads show that if you'd invested in stocks that met the criteria for the S&P Platinum Portfolio, you would have walloped the S&P 500 by more than two to one over the past 11 years. But neither of these portfolios actually existed during the entire period back-tested.

The problem with back testing, says David Leinweber, managing director at First Quadrant, a money-management firm in Pasadena, is that it can be manipulated to show nearly anything. To prove his point, Leinweber came up with the following: Would you believe that in the 10 years between 1983 and 1993 you could have used the production of butter in Bangladesh to predict how well the S&P 500 index would perform? On average, Leinweber found, when butter production was up 1%, the S&P 500 was up 2% the next year. Conversely, if butter production was down 10%, you could predict the S&P 500 would be down 20%.

Investment companies--including Merrill Lynch and S&P--argue that back testing isn't misleading because the ads explain that the results aren't based on real performance. Securities regulators seem to take a dim view of the technique, but they do allow it in limited circumstances. "Back testing has always been a suspect class of information," says the Securities and Exchange Commission's Barry Miller. "When you look backwards, you're only going to show what's good."

True believers may be interested to know that the latest indications are that Bangladeshi butter production is flat. --Laura Washington