In: Statistics and Probability
a) A data is collected from Lab A. Sample mean is 12, SD is 2.4 and sample size if 16. Another set of data from Lab B have a mean of 10 (assuming SDB is also 2.4 and nB=16). If we choose α = 0.05, do you think mean of Lab B is close enough to be considered the “same” as that of Lab A? Why?
b) Same as problem 4), except SD of Lab B is SDB=4.4. If we choose α = 0.05, do you think the mean of Lab B is close enough to be considered the “same” as that of Lab A? Why?
(a)
Data:
n1 = 16
n2 = 16
x1-bar = 12
x2-bar = 10
s1 = 2.4
s2 = 2.4
Hypotheses:
Ho: μ1 = μ2
Ha: μ1 ≠ μ2
Decision Rule:
α = 0.05
Degrees of freedom = 16 + 16 - 2 = 30
Lower Critical t- score = -2.042272449
Upper Critical t- score = 2.042272449
Reject Ho if |t| > 2.042272449
Test Statistic:
Pooled SD, s = √[{(n1 - 1) s1^2 + (n2 - 1) s2^2} / (n1 + n2 - 2)] = √(((16 - 1) * 2.4^2 + (16 - 1) * 2.4^2)/(16 + 16 -2)) = 2.4
SE = s * √{(1 /n1) + (1 /n2)} = 2.4 * √((1/16) + (1/16)) = 0.848528137
t = (x1-bar -x2-bar)/SE = 2.357022604
p- value = 0.025143982
Decision (in terms of the hypotheses):
Since 2.357022604 > 2.042272449 we reject Ho and accept Ha
Conclusion (in terms of the problem):
There is sufficient evidence that Lab B is significantly different from Lab A
(b)
Data:
n1 = 16
n2 = 16
x1-bar = 12
x2-bar = 10
s1 = 2.4
s2 = 4.4
Hypotheses:
Ho: μ1 = μ2
Ha: μ1 ≠ μ2
Decision Rule:
α = 0.05
Degrees of freedom = 16 + 16 - 2 = 30
Lower Critical t- score = -2.042272449
Upper Critical t- score = 2.042272449
Reject Ho if |t| > 2.042272449
Test Statistic:
Pooled SD, s = √[{(n1 - 1) s1^2 + (n2 - 1) s2^2} / (n1 + n2 - 2)] = √(((16 - 1) * 2.4^2 + (16 - 1) * 4.4^2)/(16 + 16 -2)) = 3.544
SE = s * √{(1 /n1) + (1 /n2)} = 3.54400902933387 * √((1/16) + (1/16)) = 1.252996409
t = (x1-bar -x2-bar)/SE = 1.596173769
p- value = 0.120931822
Decision (in terms of the hypotheses):
Since 1.596173769 < 2.042272449 we fail to reject Ho
Conclusion (in terms of the problem):
There is no sufficient evidence that Lab B is significantly different from Lab A.