资源环境科技发展态势分析平台

The Trump administration has dramatically weakened federal fuel economy and greenhouse gas (GHG) standards for cars and light trucks. The recently finalized standards will be about 13 percent less stringent than the Obama standards they replace, and the Trump administration is blocking states’ efforts to mandate higher electric vehicle sales. Weaker standards are a major part of the Trump administration’s efforts to undo Obama’s climate policies, although they are being challenged in federal court.

With the upcoming presidential election, Democratic politicians and advocacy groups have proposed ambitious GHG policies for passenger vehicles for the rest of the 2020s and the early 2030s. For example, Biden endorses strengthening GHG standards, and the House Select Committee on the Climate Crisis calls for 100 percent zero-emission vehicle sales by 2035. Given the potential for electric vehicles to reduce emissions, these proposals have focused on promoting battery innovation and consumer adoption of the technology.

The attention devoted to electric vehicles is understandable, but these proposals have largely ignored two other technologies that are entering the market and potentially transforming light-duty transportation: transportation network services (such as Uber and Lyft) and automated driving. Transportation network services are already affecting how people travel, and the effects of automated driving could be even more drastic, although considerable uncertainty exists about how much and how quickly transportation network services and higher levels of vehicle automation will penetrate the market and affect vehicle use.

Unfortunately, the federal fuel economy and GHG standards are poorly equipped to handle these technologies. Vehicle manufacturers create products that are used differently from one another over their lifetimes. For example, a small sport utility vehicle typically has fewer lifetime miles than a pickup truck (both are classified as light trucks). However, the fuel economy and GHG standards largely ignore these differences—essentially treating both as the same truck in terms of lifetime miles traveled.

This situation is unfair to the manufacturers because the program provides too much credit to some manufacturers to reduce their vehicles’ emissions rates, and too little credit to other manufacturers. It is also unfair to the public because it distorts incentives to reduce emissions rates, raising the costs of the standards. New technologies will likely exacerbate the situation—for example, midsize and large cars are much more likely than small cars to be used for transportation network services.

Although this difference between agencies’ assumptions and real-world driving may appear to be a minor detail, I explain how this situation can substantially distort manufacturer incentives to reduce emissions, thereby raising the costs of the fuel economy and GHG standards. More specifically, combining economic theory with real-world driving data, I make four points:

1. In theory, systematic differences between actual lifetime miles and regulatory agency assumptions can distort manufacturer incentives to reduce emissions. The current standards create too much incentive to reduce emissions for vehicles that are driven relatively little.
2. Actual real-world driving differs by 10–15 percent across typical models. For example, over its lifetime, the Toyota Camry is driven roughly 15 percent more than the Hyundai Sonata; both are midsize cars.
3. The data show that because of these differences, marginal incentives to reduce emissions are typically about 10–15 percent higher or lower than is economically efficient. The distortion could be eliminated by crediting a manufacturer’s vehicles according to estimated future lifetime miles.
4. Accounting for cross-model variation in driving can reduce the costs of achieving the standards by up to 30 percent, or perhaps $1 billion per year. These numbers represent rough estimates that future work can refine.
   
   

In short, the regulatory agencies make certain assumptions about how much vehicles are driven, and the purpose of this paper is to demonstrate the benefits of using real-world driving data to account for differences across vehicles in lifetime miles traveled. The conclusion explains three approaches to implementing the system, which illustrate tradeoffs among equity, cost effectiveness, and uncertainty for manufacturers. All of the approaches can be implemented easily given existing technology and data, and all of them would reduce total compliance costs.

My analysis builds on two previous papers. Greenstone et al. (2017) advocate using real-world driving behavior instead of Environmental Protection Agency (EPA) assumptions on driving, but they do not estimate the benefits of doing so. In contrast, I quantify the distortions that the EPA assumptions create and the benefits of relying on real-world driving behavior. Jacobsen et al. (2020) use data from California to estimate lifetime miles for individual vehicle models (such as the Ford Focus) and show similar cross-model variation to what I find using the National Household Travel Survey (NHTS), which is a nationally representative sample. They show that this variation causes a carbon tax to be more cost-effective than GHG emissions standards, whereas I consider how to use this variation to improve the economic efficiency of the standards themselves. Note that although transportation network services and automated driving help motivate this analysis, I do not explicitly model them. Instead, I assess the potential benefits of improving the accuracy of estimated lifetime miles traveled. Over the long term, these benefits will likely increase as transportation network services and automated driving affect how vehicles are used.