In: Statistics and Probability
Packages of mixed nuts made by a certain company contain four types of nuts. The percentages of nuts of Types 1, 2, 3, and 4 are advertised to be 40%, 30%, 20%, and 10%, respectively. A random sample of nuts is selected, and each one is categorized by type.
(a)
If the sample size is
n = 200
and the resulting test statistic value is
X2 = 17.5,
what conclusion would be appropriate for a significance level of 0.001? (Use a table or technology.)
The P-value is less than the significance level of α = 0.001, so we reject H0. We have convincing evidence that the percentages of nuts of the different types are not as advertised.The P-value is greater than the significance level of α = 0.001, so we fail to reject H0. We have convincing evidence that the percentages of nuts of the different types are not as advertised. The P-value is greater than the significance level of α = 0.001, so we fail to reject H0. We do not have convincing evidence that the percentages of nuts of the different types are not as advertised.The P-value is less than the significance level of α = 0.001, so we reject H0. We do not have convincing evidence that the percentages of nuts of the different types are not as advertised.
(b)
If the random sample had consisted of only 40 nuts, would you use the chi-square goodness-of-fit test? Explain your reasoning.
If the sample consisted of only 40 nuts,
the expected value for Type 1 =,
the expected value for Type 2=
the expected value for Type 3 =
the expected value for Type 4
Because the expected value for ---Select--- every nut type at least one nut type is ---Select--- greater less than 5, the sample size ---Select--- is is not large enough to use the chi-square goodness-of-fit test.
Solution :
a) The value of the test statistic is X2 = 17.5.
Degrees of freedom = (k - 1) = (4 - 1) = 3
(Where, k is number of nut types.)
The p-value for the test statistic is given as follows :
P-value = P(X2 > value of the test statistic)
P-value = P(X2 > 17.5)
P-value = 0.0006
Significance level = 0.001
(0.0006 < 0.001)
Conclusion :
The P-value is less than the significance level of α = 0.001, so we reject H0. We have convincing evidence that the percentages of nuts of the different types are not as advertised.
b) Sample size for nuts = 40
The expected value for Type 1 = (40 × 0.4) = 16
the expected value for Type 2 = (40 × 0.3) = 12
the expected value for Type 3 = (40 × 0.2) = 8
the expected value for Type 4 = (40 × 0.1) = 4
Because the expected value for at least one nut type is less than 5, therefore sample size is not large enough to use the chi-square goodness-of-fit test.
Please rate the answer. Thank you.