Question

Help with both 3 and 4

Question 3. (3 points each) For each situation described in a to d i. Describe what it means in that context to make a Type I and Type II error ii. Indicate whether it makes more sense to use a relatively large significance level (such as α-0. I 0 ) or a relatively smal l significance level (such as α-0.01 ). Testing a new drug with potentially dangerous side effects to see if it is significantly better than the drug currently in use I prescribed to millions of people a. is found to be more effective, it will be b. Using your statistics class as a sample to see if there is evidence of a difference between male and female students in how many hours are spent watching television per week. Testing to see if a well-known company is lying in its advertising. If there is evidence that the company is lying, the Federal Trade Commission will file a lawsuit against them. C. d. Testing to see whether taking a vitamin supplement each day has significant health are no (known) harmful si Question 40points A study was conducted to see if there is evidence that a recorded phone call is more effective than a mailed flyer in getting voters to support a certain candidate. The study assumes a significance level of a-0.05 a. What is the conclusion in the context of this study if the p-value for the test is 0.027(2pt) b. In the conclusion in part a, which type of error are we possibly making: Type I or Type II? Describe what that type of error means in this situation. points) e What is the conclr the test is 0.187 @ poins) d. In the conclusion in part c, which type of error are we possibly making: Type I or Type I1? Describe what that type of error means in this situation. (3 points)

Answer 1

3.

a.

i. The Type 1 error will be if the new drug is not effective but we conclude that it is effective and the Type 2 error will be if the new drug is effective but we conclude that it is not effective.

ii. It makes more sense to use a small significance level because the new drug can be prescribed to millions of people and we must have more confidence in its effectiveness.

b.

i. The Type 1 error will be there is no difference between male and female students in how many hours are spent watching television per week but we concluded that there exists a difference and the Type 2 error will there exist a difference but we concluded that there does not exist a difference.

ii. It makes more sense to use a 0.10 level of significance because a 90% confidence level will be sufficient to consider that male and female students differ in terms of how many hours are spent watching television per week.

c.

i. The Type 1 error will be the company is not lying in its advertising but we concluded that it is lying and the Type 2 error will be the company is lying in its advertising but we concluded that it is not lying.

ii. Since this is a critical case, we must use a significance level of 0.01 to have more confidence.

d.

i. The Type 1 error will be vitamin supplement does not have significant health benefits but we concluded that it has and the Type 2 error will be the vitamin have significant health benefits but we concluded that it does not have.

ii. Since there are no harmful side effects of the supplement, it makes more sense to use a 0.10 level of significance.

4.

a. Since the p-value is less than the level of significance we will conclude that a recorded phone call is more effective than a mailed flyer in getting voters to support a certain candidate.

b. In the conclusion in part a, we are possibly making Type 1 error. The Type 1 error in this situation means that recorded phone call is not more effective than a mailed flyer in getting voters to support a certain candidate but we concluded that recorded phone call is more effective than a mailed flyer in getting voters to support a certain candidate.

c. Since the p-value is greater than the level of significance we will conclude that a recorded phone call is not more effective than a mailed flyer in getting voters to support a certain candidate.

d. In the conclusion in part c, we are possibly making Type 2 error. The Type 2 error in this situation means that recorded phone call is more effective than a mailed flyer in getting voters to support a certain candidate but we concluded that recorded phone call is not more effective than a mailed flyer in getting voters to support a certain candidate.