In: Statistics and Probability
In the population, the average IQ is 100 with a standard deviation of 15. A team of scientists wants to test
a new medication to see if it has either a positive or negative effect on intelligence, or no effect at all. A
sample of 30 participants who have taken the medication has a mean of 105. It is assumed that the data are
drawn from a normally distributed population. Did the medication affect intelligence, using
α= 0.05?
a. State hypotheses appropriate to the research question.
(b) Describe what test would you use and state the reasons for your choice.
(c) Draw a conclusion in the context of the problem using the p-value.
(d) Construct a 95% CI for μ. Conclude in the context of the problem.
(e) Compute the power if the true population mean is 110.
a) to test medication affect intelligence the null and alternative hypotheses are
Ho : = 100
H1 : 100
b) Here we uses the standard normal (Z ) test because sample size n 30 and population standard deviation is known .
c) test statistic
Z = (xbar -) /(/n )
Z = (105 - 100 )/( 15/30)
Z = 1.83
p-value for Z =1.83 and two tailed test
p-value = 2* P( Z > 1.83)
p-value =2* 0.0336 =0.0673
Decision rule : Reject Ho if p-value < , otherwise fail to reject Ho
p-value = 0.0673 > 0.05
Decision : We reject the null hypothesis Ho
conclusion : There is no sufficient evidence to support the claim that medication affect intelligence
d) 95% confidence interval for
xabr - Za/2*(/n ) < < xbar + Za/2 *(/n)
for a= 0.05
Z0.025 = 1.96
105 - 1.96*(15/30) < < 105 + 1.96 *(15/15)
99.63 < < 110.37
We are 95% confident that true mean IQ lies between in this interval.