In: Math
A recent study found that children who watched a cartoon with food advertising ate, on average, 28.6 grams of crackers as compared to an average of 18.8 grams of crackers for children who watched a cartoon without food advertising. Suppose that there were 61 children in each group, and the sample standard deviation for those children who watched the food ad was 8.7 grams and the sample standard deviation for those children who did not watch the food ad was 7.7 grams. Complete parts (a) and (b) below.
b. Assuming that the population variances are equal, construct 95% confidence interval estimate of the difference μ1−μ2 between the mean amount of crackers eaten by the children who watch and do not watch the food ad.
___≤ μ1−μ2 ≤ ___ (Round to two decimal places as needed.)
Solution:
Confidence interval for difference between two population means is given as below:
Confidence interval = (X1bar – X2bar) ± t*sqrt[Sp2*((1/n1)+(1/n2))]
Where Sp2 is pooled variance
Sp2 = [(n1 – 1)*S1^2 + (n2 – 1)*S2^2]/(n1 + n2 – 2)
We are given
n1 = 61
n2 = 61
df = n1 + n2 – 2 = 61 + 61 – 2 = 120
Confidence level = 95%
Critical t value = 1.9799
(by using t-table)
X1bar = 28.6
X2bar = 18.8
S1 = 8.7
S2 = 7.7
Sp2 = [(n1 – 1)*S1^2 + (n2 – 1)*S2^2]/(n1 + n2 – 2)
Sp2 = [(61 – 1)*8.7^2 + (61 – 1)*7.7^2]/(61 + 61 – 2)
Sp2 = 67.4900
(X1bar – X2bar) = 28.6 – 18.8 = 9.8
t*sqrt[Sp2*((1/n1)+(1/n2))] = 1.9799*sqrt[67.4900*((1/61)+(1/61))]
t*sqrt[Sp2*((1/n1)+(1/n2))] = 1.9799*1.4875
t*sqrt[Sp2*((1/n1)+(1/n2))] = 2.9452
Confidence interval = (X1bar – X2bar) ± t*sqrt[Sp2*((1/n1)+(1/n2))]
Confidence interval = 9.8 ± 2.9452
Lower limit = 9.8 - 2.9452 = 6.8548
Upper limit = 9.8 + 2.9452 = 12.7452
Confidence interval = (6.8548, 12.7452)
6.85 ≤ µ1 - µ2 ≤ 12.75