In: Statistics and Probability
.An e-commerce research company claims at most59%of graduate students have bought merchandise on-line. A consumer group is suspicious of the claim and wants to test it. They collected a random sample of 135graduate student and found that50 graduate students have not bought merchandise on-line. Is there enough evidence to show that the true proportion is at most 59%? Conduct the test at 0.1level of significance. (Please show all 5 steps involved
Solution:
Claim: p is at most 59%
i.e. p 0.59
So , the null and alternative hypothesis are
H0 : p 0.59 vs Ha: p > 0.59
Now,
sample size n = 135
Number of student have not bought merchandise on-line is 50
So ,
Number of student have bought merchandise on-line is 135 - 50 = 85
Let be the sample proportion.
= x/n = 85/135 = 0.6296
The test statistic z is
z =
= (0.6296 - 0.59)/[0.59*(1 - 0.59)/135]
= 0.94
Test statistic z = 0.94
Right tailed test
so .
p value = P(Z > z) = 1 - P(Z < z) = 1 - P(Z < 0.94) = 1 - 0.8264 = 0.1736
p value = 0.1736
p value is greater than level of significance 0.1
So , Do not reject the null hypothesis.
There is not sufficient evidence to reject the claim.