In 1988, the average gasoline retail price of one of the major oil companies had been $1.25 per gallon in a certain large market area of the country, Houston, Texas. Since the company was concerned about the aggressive pricing of its competitors (gasoline, of course, is a commodity product which typically competes on price), its general manager tried to take measures to reduce the retail price per gallon (that is, the price you and I pay at the pump). After several months of trying to push down prices, she was interested in determining whether or not the then-current price was significantly less than $1.25. A random sample of n = 49 of their gasoline stations was selected, and the average price was determined to be $1.20 per gallon. Assume that the standard deviation of the population was σ = $0.14. Note: (b), (c), and (d) below require numerical answers.
(a) At the 95% confidence level, test to determine whether the measures taken by the company were effective in reducing the average price. Please use the six-step hypothesis-testing framework we employed in class, and write out the last three steps in this table.
|
H0: µ ≥ $1.25
|
|
Ha: µ < $1.25
|
|
n = 49, α = .05
|
(b) What is the p-value associated with the above sample result?
(c) What is the probability of committing a Type II error, β, if the actual price per gallon is $1.19 per gallon?
(d) What is the "power of the test," i.e., what is (1 - β)?