摘要：Objectives. We sought to examine the association between policies governing access to tobacco during adolescence and subsequent adult smoking. Methods. We analyzed adult smoking data from the 1998 through 2006–2007 administrations of the US Current Population Survey Tobacco Use Supplement by employing a quasi experimental approach. Participants (n = 105 519) were adults, aged 18 to 34 years at the time of the survey. Smoking outcomes included having ever smoked 100 cigarettes, smoking at the time of the survey, and having smoked 10 or more cigarettes a day conditioned on being an ever smoker. These were predicted from exposure to state youth access policies at age 17 years. Results. Four of the 9 policies exhibited significant associations with reduced prevalence of 1 or more smoking outcomes, primarily among women. Lesser effects for other policies could not be ruled out. Conclusions. Restrictions on youth access to tobacco might lead to reduction in smoking prevalence later in adulthood. The effect might be limited to women; we estimate that having all policies in place could be associated with a 14% reduction in lifetime smoking prevalence for women, and an additional 29% reduction in heavy smoking among ever smokers. Both opponents of smoking and purveyors of cigarettes have recognized the significance of adolescence as the period during which smoking behaviors are typically developed. 1,2 Accordingly, initiatives to curb youth smoking were among the first federal policy restrictions placed on cigarette sales in the United States. 3,4 Adoption of these initiatives was accelerated by passage of the 1992 Synar Amendment to the Federal Alcohol, Drug Abuse, and Mental Health Administration Reorganization Act, which mandated withholding federal block-grant money from states that failed to prohibit distribution of tobacco products to persons younger than 18 years, or failed to enforce such prohibitions. Various measures were implemented by individual states to increase retailer compliance with de jure purchase ages, such as restricting physical access to cigarette vending machines and banning the sale of single cigarettes. 5,6 Adaptation of these policies was partly motivated by community intervention studies suggesting that more uniform compliance with legal purchase age policies would reduce smoking rates among youths. 7–11 Some postimplementation studies have suggested that youth access restrictions are effective at reducing smoking among adolescents, 12–14 whereas other studies have cast doubt on their effectiveness. 6,15–17 Furthermore, opponents argue that youth access policies could inadvertently glamorize smoking as a sophisticated adult behavior, thus reinforcing messages historically associated with tobacco advertising. 18 Hence, some argue that youth access restrictions divert resources away from well-established and universally targeted tobacco control policies, such as clean indoor air policies, price increases, and media campaigns. 16,19 Youth access measures were not designed to merely delay smoking, but presumably to deter progression by delaying onset or reducing the intensity of smoking during adolescence. As such, reductions in smoking that persist into adulthood are the proper benchmarks by which these policies should be assessed. In the current study, we examined whether youths who face a restrictive policy environment are less likely to smoke as adults. We analyzed long-term associations between state youth access policies and subsequent adult smoking by taking advantage of state-by-state and year-by-year policy differences as states adopted various measures in response to the Synar Amendment. We expect that policies effective in mitigating youth smoking also influence subsequent adult smoking. It has been shown, for example, that exposure to stricter drinking age laws are associated with lower prevalence of alcohol problems in adulthood, but to our knowledge, parallel studies have not been conducted for tobacco policy. 20–22 Hence, we examined whether policy encountered during adolescence is associated with smoking behaviors during adulthood. This hypothesis is consistent with contemporary neurobiological views of adolescence as a critical period for the development of addiction. 23–25
