Significance Tests: The Basics Section 9.1 again… Significance Tests: The Basics
Type I and Type II Errors If we reject 𝐻 0 when 𝐻 0 is true, we have committed a Type I error. If we fail to reject 𝐻 0 when 𝐻 0 is false, we have committed a Type II error.
Another way to look at it!
Examples If someone is on trial for murder: 𝐻 0 : 𝐻 𝑎 : Type I error – we reject that they are innocent when we shouldn’t have…meaning we convicted an innocent person. Type II error – we let a guilty person go free. Which is worse?
Examples If someone is on trial for stealing a candy bar: 𝐻 0 : 𝐻 𝑎 : Type I error – we reject that they are innocent when we shouldn’t have…meaning we convicted an innocent person. Type II error – we let a guilty person go free. Which is worse?
Put your notes on the floor. What is Type I error? What is Type II error?
Example The manager of Wendy’s wants to reduce the proportion of drive-through customers who have to wait more than two minutes on their order. Based on store records, the proportion is currently p=0.63. To reduce this proportion, the manager assigns an additional employee to assist with drive-through orders. During the next month, the manager will collect a random sample of drive-through times and test the hypotheses: 𝐻 0 :p=0.63 𝐻 0 :𝑝<0.63 Describe a Type I and Type II error in this setting and explain the consequences of each.
Significance and Type I Error The Significance level 𝛼 of any fixed level test is the probability of a Type 1 error. If given the chance, consider the consequences of a Type I error before choosing a significance level.
Example For a truckload of potatoes, we are testing the proportion that have blemishes. 𝐻 0 :𝑝=0.08 𝐻 0 :𝑝>0.08 Suppose that the potato-chip producer decides to carry out this test on a SRS of 500 potatoes using a 5% significant level.
Example
Power and Type II Error The power of a test against any alternative is one minus the probability of a Type II error for that alternative. 𝑃𝑜𝑤𝑒𝑟=1−𝛽 Power is NOT the compliment of Type I error! Beta is NOT the compliment of Type I error!
How are they related? 𝜶 𝜷 Power
Potatoes The potato-chip producer wonders whether the significance test of 𝐻 0 :𝑝= .08 vs. 𝐻 𝑎 :𝑝>.08 based on a random sample of 500 potatoes has enough power to detect a shipment of 11% blemished potatoes.
Homework Pg. 547 (19-25, 27-30)