摘要：Objectives. We examined the effects of a 2009 increase in alcohol taxes in Illinois on alcohol-related fatal motor vehicle crashes. Methods. We used an interrupted time-series design, with intrastate and cross-state comparisons and measurement derived from driver alcohol test results, for 104 months before and 28 months after enactment. Our analyses used autoregressive moving average and generalized linear mixed Poisson models. We examined both population-wide effects and stratifications by alcohol level, age, gender, and race. Results. Fatal alcohol-related motor vehicle crashes declined 9.9 per month after the tax increase, a 26% reduction. The effect was similar for alcohol-impaired drivers with positive alcohol levels lower than 0.15 grams per deciliter (−22%) and drivers with very high alcohol levels of 0.15 or more (−25%). Drivers younger than 30 years showed larger declines (−37%) than those aged 30 years and older (−23%), but gender and race stratifications did not significantly differ. Conclusions. Increases in alcohol excise taxes, such as the 2009 Illinois act, could save thousands of lives yearly across the United States as part of a comprehensive strategy to reduce alcohol-impaired driving. Effects of alcohol tax rates on drinking and alcohol-related problems have been extensively studied over the past half century. A 2009 meta-analysis found 112 studies containing more than 1000 estimates of the relationship of alcohol taxes and prices to drinking. 1 Results show that a 10% increase in the price of alcoholic beverages is associated with a 5% to 8% decrease in drinking. A similar systematic review of 50 articles containing 340 estimates of alcohol price and tax effects on a wide range of social and health problems associated with drinking found that alcohol tax increases result in significant declines in chronic disease (e.g., cirrhosis, esophageal cancer), sexually transmitted infections, injuries, violence, and motor vehicle crashes. 2 The US Department of Health and Human Services Community Preventive Services Task Force also reviewed this evidence and recommended increasing alcohol taxes to reduce excessive drinking and related harms. 3 However, the great majority of the studies that have evaluated the effects of alcohol tax changes date from the 1970s, 1980s, and 1990s, and their results have not been reflected in public policy in the United States—when inflation is taken into account, real alcohol tax rates are only about half what they were in the 1960s. 4 Lower real tax rates, along with broader economic changes in recent decades, have made alcoholic beverages much more affordable than in times past. For example, drinking 1 drink per day of the cheapest spirits required 15 times the fraction of income in 1950 that it did in 2011. 5 Even more noteworthy, the cost of very heavy drinking (≥ 10 drinks/day) required 45% of mean disposable income in 1950, but only 3% in 2011. One result of such dramatically increased affordability of alcohol is that the small alcohol tax increases that have been implemented in the United States recently cause price increases for alcoholic beverages that are a much smaller fraction of personal income than would have occurred in previous decades, when most previous evaluations of alcohol tax increases were conducted. The potential importance of affordability was recently reinforced by Room et al., who reported that tax reductions in Denmark and Sweden did not result in expected increases in alcohol consumption, a result the authors attributed to the level of affluence of these countries, where alcohol was already highly affordable. 6 In short, recent economic and social changes emphasize the importance of evaluating the effect of recent increases in alcohol taxes on excessive alcohol use and related harms. The mechanisms by which alcohol taxes reduce motor vehicle crash rates are well established: tax rates affect retail price, and price affects amount and patterns of drinking, including excessive drinking, which affect the risk of alcohol-related motor vehicle crashes. 1,3,7 Drinking by motorists increases risk of serious car crashes, with risks rising exponentially beyond 1 or 2 drinks. 8 A systematic review of 21 studies containing 34 independent estimates of tax and price effects on crash rates reveals a significant inverse variance–weighted overall effect ( r = −0.112). 2 Two studies published since that systematic review largely confirm alcohol tax effects on crash rates, although the consistency and magnitude of observed effects varies. 9,10 Replication studies are important because alcohol-related motor vehicle crashes continue to result in more than 10 000 deaths and half a million injuries annually, representing a leading public health problem associated with alcohol use that is deserving of continued policymaker attention. 7,11 Although the population-wide effect of alcohol taxes on excessive alcohol consumption and alcohol-impaired driving is well established, Elder et al. note that research to date has paid little attention to possible differences in alcohol tax effects in different segments of the population; they call for additional analyses of demographic subgroups. 3 Staras et al. recently highlighted the potential importance of subgroup analyses in an evaluation of the effects of an alcohol tax increase in Illinois on sexually transmitted infection rates. 12 They found noticeably larger effects (i.e., reductions in infection rates after the tax increase) among Blacks than Whites, perhaps because of differing exposure risks, levels of disposable income, and other factors. To address the need for more current data on the effects of alcohol taxes on alcohol-related motor vehicle crashes as well as the need to better characterize the effects of alcohol taxes on specific subgroups, we evaluated the effects of a September 2009 increase in alcohol excise taxes on beer, wine, and spirits in the State of Illinois on fatal alcohol-related motor vehicle crashes. We assessed the overall effect of the tax increase on fatal motor vehicle crashes, as well as effects on major population subgroups.
