• Car Allowance Rebate System (CARS), known as "cash for clunkers", was a $3 billion U.S. federal scrappage program.

• It was intended to provide economic incentives to U.S. residents to purchase a new, more fuel-efficient vehicle when trading in a less fuel-efficient vehicle.

• The program officially started on July 1, 2009 and ended on August 24, 2009, as the appropriated funds were exhausted.

• Nearly 700,000 transactions occurred during the program.

• This project is to analyze the success of CARS program.

• Source Data: nhtsa.gov

1. Success Measurement
   • Market Size success: Total number of CARS transactions paid
   • Fuel Efficiency success: Percentage of mpg improvement
   • Profitablity success: Total voucher amount, Voucher amount per capita

2. West Coast Consumers Purchase More Fuel Efficient Cars?

3. Behavioral Patterns
   • New car types for different trade-in vehicle types
   • Country of manufacture for trade-in and new vehicles

4. Data Sufficiency

5. Conclusion

• Goal: Market Size Success
• Metric: Total Number of CARS Transactions Paid per State

• Goal: Fuel Efficiency Success
• Metric: New Vehicles Mileage / Trade-in Mileage - 1 (US: 58% improvement)

• Goal: Profitablity Success
• Metric: Total Voucher Amount per State

• Goal: Profitablity Success
• Metric: Voucher Amount per Capita (2010 Population Estimates) per State

• West Coast: CA, OR, WA, AK, HI
• Box Plot: Both trade-in and new vehicles have higher mileage in West Coast

• Hypothesis Testing for Trade-in Cars (Sample size different)
• H0: Trade-in West Coast MPG mean = Trade-in Others MPG mean (H1: > )
• Trade-in cars from West Coast are more fuel efficient than other regions

## 
##  Welch Two Sample t-test
## 
## data:  Trade_in_West_Coast and Trade_in_Others
## t = 29.966, df = 132950, p-value < 2.2e-16
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
##  0.2207418       Inf
## sample estimates:
## mean of x mean of y 
##  15.89800  15.66443

• Hypothesis Testing for New Cars (Sample size different)
• H0: New West Coast MPG mean = New Others MPG mean (H1: > )
• Newly-bought cars from West Coast are more fuel efficient than other regions

## 
##  Welch Two Sample t-test
## 
## data:  New_West_Coast and New_Others
## t = 67.642, df = 122450, p-value < 2.2e-16
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
##  1.526392      Inf
## sample estimates:
## mean of x mean of y 
##  26.20759  24.64316

• Passenge Cars, Category 1 / 2 Trucks -> Passenger Cars
• Category 3 Trucks -> Category 2 Trucks

• MPG: Passenger Car > Category 1 Truck > Category 2 Truck > Category 3 Truck
• Customers tend to buy more fuel-efficient cars
• One of the reasons might be the higer gas price

• Most of the customers prefer to buy Japanese cars

• Possible reason 1: Japanese cars are more fuel-effencient

• Possible reason 2: Japanese cars have lower price

• Data is not provided sufficiently yet.

• Need more information about demographic distribution in different states: such as the total amount of people who own cars, car make distributions, etc.

• Gas price increase -> people buying more fuel-efficient cars?

• Without knowing these, we can hardly conclude that the CARS program is "widely successful".

• Ideally we should perform a before-after study.

• California has the largest paid transactions, voucher amount and voucher amount per capita.

• Utah has the best fuel efficiency improvement.

• West Coast cusotmers significantly purchase more fuel efficient vehicles than other regions.

• Cusomers tend to buy more Japanese cars and Passanger Cars.

• To conclude whether the program is "widely successful", we need more demographic and economic data. We cannot exclude the effect of gas price increase.

• Ideally we should perform a before-after study.