In: Statistics and Probability
You wish to test the following claim (H1H1) at a significance
level of α=0.02α=0.02.
Ho:p1=p2Ho:p1=p2
H1:p1>p2H1:p1>p2
You obtain 113 successes in a sample of size n1=450n1=450 from the
first population. You obtain 91 successes in a sample of size
n2=399n2=399 from the second population. For this test, you should
NOT use the continuity correction, and you should use the normal
distribution as an approximation for the binomial
distribution.
What is the critical value for this test? (Report answer accurate
to three decimal places.)
critical value =
What is the test statistic for this sample? (Report answer accurate
to three decimal places.)
test statistic =
The test statistic is...
This test statistic leads to a decision to...
As such, the final conclusion is that...
Here we have given that,
Claim: To check whether the first population proportion is greater than the second population proportion.
The null and alternative hypotheses is as follows,
Ho: P1=P2
v/s
H1:P1 > P2
we have given that,
n1= 1st Sample size from first population =450
x1=number of success from the first sample=113
n2= 2nd Sample size from second population=399
x2=number of success from the second sample=91
Now we estimate the proportion p as
=1st sample proportion =
= 2nd sample proportion =
We are using the 2 sample proportion test and normal distribution as an approximation for the binomial distribution.
Now, we can find the critical value.
= level of significance= 0.02
This is right-tailed test.
Z-critical =2.05 Using EXCEL software = NORMSINV(probablity=0.02)
Now, we can find the test statistics for sample
=
=0.786
The test statistics for this sample is 0.786
Decision:
Z-statistics (0.786) < Z-critical (2.05)
The test statistics is not in the critical region.
Conclusion:
We fail to reject null hypothesis Ho.
There is not sufficient evidence to warrant rejection of the claim that the first population proportion is greater than the second population proportion.