Abstract

Fuel efficiency in cars varies widely between different makes and models depending on a variety of factors including car size, fuel displacement, and more. The Environmental Protection Agency (EPA) offers a public facing data set of fuel efficiency estimates for a range of cars to assist the public in their car purchasing decisions.

I targeted two variables in the data, engine displacement and class of car, and examined how they might affect fuel efficiency (based on highway miles per gallon). I created a scatterplot of highway mpg and engine displacement, which showed a strong negative correlation; higher engine displacement typically meant that a car would have lower highway mpg. This scatterplot had several outliers, which raised the question of what other factors might impact highway mpg. By creating a bar graph of highway mpg and car class, I found that large cars have a lower highway mpg than small cars. This finding supported my hypothesis that the outliers in the engine displacement graph can be explained by car size.

Introduction

The data set used in this project is “Fuel economy data from 1999 to 2008 for 38 popular models of cars,” which is derived from EPA fuel economy data posted on https://fueleconomy.gov/. Potential problems with the data include that the data in this project is somewhat outdated, as fueleconomy.gov has data available up to 2021. Additionally, according to the data guide from the EPA, some vehicles were not included in the dataset if they weighed more than 8,500 pounds, if their fuel economy data was not available at the time of publication, or if the availability of the vehicle was restricted (EPA 2008). Additionally, the 2008 data guide states that new testing methods implemented in 2008 caused mpg estimates for 2008 and later model cars to be “noticably lower” than those for previous years, so data for 2008 models may be difficult to compare to data for older models (EPA 2008).

Description of the Data

“Fuel economy data are the result of vehicle testing done at the Environmental Protection Agency’s National Vehicle and Fuel Emissions Laboratory in Ann Arbor, Michigan, and by vehicle manufacturers with oversight by EPA” (EPA 2021). The dataset only includes cars from the 1999 and 2008 studies (not all years in between as the title might suggest). Miles per gallon (for city and highway) is an estimate provided by the EPA.

Variables

Variable Description
manufacturer manufacturer name
model model name
displ engine displacement in liters
year year of manufacture
cyl number of cylinders
trans type of transmission
drv type of drive train where f=front-wheel drive, r=rear-wheel drive, and 4=4-wheel drive
cty city miles per gallon
hwy highway miles per gallon
fl fuel type
class type of car

Data Analysis

MPG and Engine Displacement

A scatterplot that maps highway mpg to engine displacement shows a strong negative correlation between the two variables. Cars that have higher engine displacement tend to have lower highway mpg, with a few noticeable outliers that are highlighted in the plot below in red.

The trend shown in this plot makes sense; the higher an engine’s displacement, the more fuel it takes in per revolution (Your Mechanic 2015). That means that high displacement engines use more fuel, and therefore are less efficient. The highlighted outliers may be explained by the following: The low displacement high mileage outliers on the left side of the graph could potentially be hybrid cars or small cars. Reviewing the data reveals that the cars at these points are the 1999 Volkswagen Beetle, a very small car, and the 1999 Volkswagon Jetta, another compact car. Smaller cars are relatively light and therefore consume less fuel. These cars may be outlier points because they are smaller and lighter than the other cars with engine displacement in the data set. The high displacement outliers on the right side of the graph could be smaller sporty cars, so though they have powerful engines they could be lighter than other cars with similarly high displacement engines. The data shows that most of these red points are two-seater Corvettes, which are relatively compact sports cars. The car at point (5.3, 25) is a Pontiac Grand Prix, which is a midsize car. The cars at the surrounding points are all SUVs and pickups, which are much larger and heavier cars than our outliers.

MPG and Class

A bar chart that compares cars of different classes by their highway mpg shows that larger cars have worse fuel efficiency than smaller cars.

Minivans, pickups, and SUVs had the worst highway mpg, and were the largest vehicle classes included in the data set. Compact and subcompact cars had the best highway mpg, and were among the smallest vehicle classes included in the data set. It may be initially surprising that the 2-seater class was at the middle of the group for highway mpg, since 2-seater cars are relatively small. However, the data set only includes one type of car in this class (the Chevrolet Corvette, 1999 and 2008 models). As the Corvette is a sports car, it has a high displacement engine that consumes more fuel than other similarly sized cars with lower displacement engines.

This graph supports our hypotheses about the outliers from the mpg/engine displacement graph; larger cars are heavier and therefore consume more fuel, while smaller cars are lighter and generally consume less fuel, unless they’re sports cars.

Conclusion

This report focused on examining the relationship between fuel efficiency, measured by highway mpg, and two variables: engine displacement and car size, as approximated by vehicle class. The data examined, which was a small segment of the EPA fuel efficiency data, showed a strong negative correlation between fuel efficiency and engine displacement - generally the higher the fuel displacement of a car, the lower the fuel efficiency. The outliers in this data relationship were all found to be small cars (compact and 2-seater cars). Further analysis of the data showed that smaller cars tend to have better fuel efficiency than larger cars. This could explain why smaller cars outperformed other cars with similar engine displacement. Additional data should be gathered to determine if the findings of this report are accurate; since there was only one type of car in the 2-seater class, I cannot be certain if these findings can be generalized to other 2-seater vehicles. Furthermore, since the data in this study only cover EPA data from 1999 and 2008, I would like to analyze more years to see if these preliminary findings hold true.

References

EPA, “2008 Fuel Economy Guide” https://www.fueleconomy.gov/feg/pdfs/guides/FEG2008.pdf

EPA, “Download Fuel Economy Data” https://www.fueleconomy.gov/feg/download.shtml

EPA, “Model Year 1999 Fuel Economy Guide” https://www.fueleconomy.gov/feg/epadata/99feg.pdf

Your Mechanic, “What is Engine Displacement” https://www.yourmechanic.com/article/what-is-engine-displacement