(FORTUNE Magazine) – If you've followed the recent debate about raising the minimum wage, you might be confused. On the one hand, 101 economists (three of them Nobel winners) recently signed a statement advocating a raise in the minimum wage from its current level of $4.25 an hour to $5.15. On the other hand, a dozen economists (three of them Nobel winners) recently wrote articles in the Wall Street Journal attacking the minimum-wage increase. Is there a right answer?

Actually, yes. Increasing the minimum wage will reduce the number of jobs. A minimum wage set above the current wage prices the least-skilled workers out of the labor market. This is an instance of the "law of demand," whereby a higher price causes people to buy a smaller quantity. Economists may not be sure of much, but one thing we are sure of is the law of demand.

So why do these 101 economists bless a raise in the minimum wage, an unambiguous economic sin? One probable reason is that they've been persuaded by the 1994 New Jersey study done by Princeton economists David Card and Alan B. Krueger. That study, based on a survey of fast-food restaurants, found that employment in New Jersey, whose state government raised the minimum wage from $4.25 to $5.05 in April 1992, rose relative to employment in Pennsylvania, which kept the federal $4.25 minimum.

There's one main problem with the New Jersey study: It's based on lousy data. Card and Krueger hired research assistants to call the fast-food restaurants and speak to the manager or the assistant manager. The researchers then asked a series of questions, two of which were on the number of full-time and part-time employees. They did this both before and after the minimum-wage increase, but the researchers never defined "part-time" or "full-time," nor did they specify if they were asking for the number of employees on that shift, that day, or that payroll period.

Researchers at the Employment Policies Institute (EPI), an employer-funded group in Washington, noted anomalies in Card and Krueger's data. One Wendy's in New Jersey, for example, which had no full-time workers and 30 part-time workers in February 1992, had, by November 1992, the same number of part-time workers, but 35 additional full-time workers. The EPI concluded: "[T]he Card-Krueger data set consistently reports employment losses where none actually took place, and employment gains far in excess of their true values." A third of the data, noted the EPI, failed even to "identify...whether [there] was a job loss or a job gain."

A more careful study of the same minimum-wage increase has been done. David Neumark of Michigan State University and William Wascher of the Federal Reserve Board analyzed payroll data from 230 restaurants in New Jersey and Pennsylvania. They found that the New Jersey raise destroyed an average of 0.76 full-time equivalent jobs per New Jersey restaurant--a 2.4% decrease in employment for each 10% increase in the minimum wage.

So any of those 101 economists who changed their mind because of the Card-Krueger study can change it back. Interestingly, Card and Krueger were not among those 101 economists.

--David R. Henderson

DAVID R. HENDERSON is a research fellow with the Hoover Institution and an economics professor at the Naval Postgraduate School in Monterey, California.