We would like to test the gas mileage of a new hybrid car engine, in particular, if it gets a better gas mileage than a previous engine, which obtained 46 mpg. We plan to take a random sample of gas mileages using a fleet of test cars. We will use a sample size of 35, and we will assume that the population standard deviation is 3.1.

If we would like to be able to detect a difference of 4 or more mpg, what is the Power of the Test?