In: Statistics and Probability
You may need to use the appropriate technology to answer this question.
Test the following hypotheses by using the
χ2
goodness of fit test.
H0: | pA = 0.40, pB = 0.40, and pC = 0.20 |
Ha: | The population proportions are not pA = 0.40, pB = 0.40, and pC = 0.20. |
A sample of size 200 yielded 60 in category A, 120 in category B, and 20 in category C. Use α = 0.01 and test to see whether the proportions are as stated in
H0.
(a)
Use the p-value approach.
Find the value of the test statistic.
__________
Find the p-value. (Round your answer to four decimal places.)
p-value =
Repeat the test using the critical value approach.
Find the value of the test statistic.
____________
State the critical values for the rejection rule. (If the test is one-tailed, enter NONE for the unused tail. Round your answers to three decimal places.)
test statistic≤:
test statistic≥:
Solution:
Given:
H0: | pA = 0.40, pB = 0.40, and pC = 0.20 |
Ha: | The population proportions are not pA = 0.40, pB = 0.40, and pC = 0.20. |
A sample of size 200 yielded 60 in category A, 120 in category B, and 20 in category C.
Level of significance = α = 0.01
Part a) Use the p-value approach.
Find the value of the test statistic.
Chi square test statistic for goodness of fit
Where
Oi = Observed Counts
Ei =Expected Counts = N * Expected proportions = 200 * Expected proportions
Thus we need to make following table
Category | Oi: Observed Frequencies | Expected Proportions | Ei: Expected Frequencies | Oi2/Ei |
---|---|---|---|---|
A | 60 | 0.40 | 80 | 45.000 |
B | 120 | 0.40 | 80 | 180.000 |
C | 20 | 0.20 | 40 | 10.000 |
N = 200 |
Thus
Find the p-value.
df = k - 1 = 3 - 1 = 2
Use excel command:
=CHiSQ.DIST.RT( x , df )
=CHiSQ.DIST.RT( 35.000 , 2 )
=0.0000
Thus p-value = 0.0000
Repeat the test using the critical value approach.
Find the value of the test statistic.
State the critical values for the rejection rule.
Use excel command:
=CHISQ.INV.RT( probability, df)
=CHISQ.INV.RT(0.01,2)
=9.210
Thus Critical value = 9.210
test statistic ≤ : NONE
test statistic ≥ : 9.210
Decision:
Since test statistic value = 35.000 > critical value = 9.210, we reject null hypothesis H0.
Conclusion:
At 0.01 level of significance , we have enough evidence to reject null hypothesis that: pA = 0.40, pB = 0.40, and pC = 0.20