A pharmaceutical company claims 90% success rate of a newly invented drug to treat arthritis pain. To examine the claim, a doctor administered the prescribed dose to 10 arthritis patients. She observed Y, the number of participants for which the drug was effective. A test is defined so as to reject Ho: p = 0.9 in favour of Ha: p< 0.9 by the rejection region {y
![A pharmaceutical company claims 90% success rate of a newly invented drug to treat
arthritis pain. To examine the claim, a doctor administered the prescribed dose to 10
arthritis patients. She observed Y, the number of participants for which the drug was
effective. A test is defined so as to reject Ho: p = 0.9 in favour of Ha: p < 0.9 by
the rejection region {y < k} where k is a positive integer. Note that p is the population
proportion of arthritis patients for which the drug was effective.
(a) State what is meant by Type I and Type II errors in this context.
(b) Find the value of a, the level of the test, if k = 6.
(c) For a = 0.05, what should be the value of k if the rejection region of the test is
{y <k}?
(d) Find the power of the test for p = 0.3, 0.5, 0.7, 0.9.
(e) Sketch a graph of the power function against p (0 ≤ p ≤ 1), and comment on how
the power changes as p changes. [Hint: You may use Table 1 in Appendix 3 of
WMS.]](/v2/_next/image?url=https%3A%2F%2Fcontent.bartleby.com%2Fqna-images%2Fquestion%2F55521067-0384-497f-95f8-f51a06d5dbdf%2F096f7558-e321-4399-80bc-1d7292e331ac%2Fdxmb7ls_processed.png&w=3840&q=75)

(As per our standard guidelines, we are supposed to answer only 3 sub-parts.)
a) In hypothesis testing, Type I and Type II errors have specific meanings:
Type I Error: In this context, a Type I error would occur if the doctor rejects the null hypothesis
p=0.9 (i.e., the drug has a 90% success rate), when in fact it is true. This means that the doctor would conclude that the drug is less effective than claimed when it actually is 90% effective.
Type II Error: A Type II error would occur if the doctor fails to reject the null hypothesis
p=0.9, when in fact the alternative hypothesis
p < 0.9 is true. In this case, the doctor would conclude that the drug is as effective as claimed (90% success rate), when it is actually less effective.
Step by step
Solved in 4 steps with 23 images




