By agreeing to make its family-oriented movies smoke-free and "discourage" smoking in films distributed under its Touchstone and Miramax brands, the Walt Disney Co. has implicitly endorsed the claim that smoking on the screen leads to smoking in real life.

While that connection may sound intuitively appealing, there is little reason to believe that decisions like Disney's will have a noticeable effect on smoking rates.

Reporting on Disney's new policy, Reuters cited research finding that "children with the highest exposure to smoking in movies were nearly three times more likely to start smoking." Anti-smoking activists, such as University of California, San Francisco professor Stanton A. Glantz, who runs the Smoke Free Movies project, go even further, asserting that cinematic cigarettes account for 52 percent of smoking initiation and that an automatic R-rating for movies with smoking "would cut movie smoking's effect on kids in half, saving 50,000 lives a year in the U.S. alone."

Those claims are based on a 2003 Lancet study that found 10- to 14-year-olds who had seen movies with many smoking scenes were more likely to try cigarettes than kids who had seen movies with fewer smoking scenes. The problem with attributing this association to cinematic smoking is that it's impossible to control for differences in personality and environment that make kids more likely to see movies with a lot of smoking in them, which already tend to be R-rated movies.

The study did take into account measures of "sensation-seeking," "rebelliousness" and "self-esteem," as well as "social influences" and "parenting characteristics." But it's unrealistic to suppose that such measures fully account for all the relevant differences. To put it another way, something distinguishes kids who see a lot of R-rated movies from kids who don't, and whatever it is — parental permissiveness, attraction to adult themes, a tendency to act out — may also affect their inclination to smoke.

Methodological difficulties aside, the size of movies' alleged effect is implausibly large, to put it mildly. Glantz says cinematic smoking accounts for even more real-life smoking than advertising does: 52 percent versus 34 percent. Is it even conceivable that exposure to movies and advertising causes 86 percent of smoking? That all other factors in life, including peers, parents and personality, together contribute only 14 percent?

At least as offensive as such patently absurd claims is the premise that every filmmaker should make his work conform to the dictates of anti-smoking activists. While Disney wishfully asserts that "cigarette smoking is a unique problem," how will it respond when activists demand that it eliminate scenes depicting sloth, gluttony and helmetless bike or motorcycle riding from its movies to promote public health?

Artistically speaking, there is something to be said for depicting people as they actually are, as opposed to the way they would be if avoiding disease and injury were always their top priority. And when it comes to smoking, movies reflect reality more accurately than anti-smoking activists claim. Overall, according to a 2005 study in the journal Chest, "contemporary American movies do not have a higher prevalence of smoking than the general U.S. population."

The study also found that "bad guys" were more likely to smoke than "good guys" and that, as in real life, smoking was associated with lower socioeconomic status. "Most investigators have concluded that smoking is portrayed as glamorous and positive," the lead author said, "but our study shows that the exact opposite is true."

Interestingly, the researchers reported that smoking was especially common in independent films, a fact they said may be because of the "anti-establishment or free-spirited" character of such movies. If anyone is making smoking seem cool, it's self-righteous busybodies like Stanton Glantz.

Jacob Sullum, a senior editor at Reason magazine, is the author of "For Your Own Good: The Anti-Smoking Crusade and the Tyranny of Public Health". He wrote this commentary for the Los Angeles Times.