In: Statistics and Probability
Fairfield Homes is developing two parcels near Pigeon Forge, Tennessee. In order to test different advertising approaches, it uses different media to reach potential buyers. The mean annual family income for 19 people making inquiries at the first development is $160,000, with a standard deviation of $37,000. A corresponding sample of 27 people at the second development had a mean of $181,000, with a standard deviation of $32,000. Assume the population standard deviations are the same. At the 0.01 significance level, can Fairfield conclude that the population means are different?
State the decision rule for 0.01 significance level: H0: μ1 = μ2; H1:μ1 ≠ μ2. (Negative values should be indicated by a minus sign.Round your answers to 2 decimal places.)
Compute the value of the test statistic. (Negative value should be indicated by a minus sign. Round your answer to 2 decimal places.)
At the 0.01 significance level, can Fairfield conclude that the population means are different?
Reject/Do no reject H0. Fairfield can/cannot conclude that the population means are different
Part a
We are given
α = 0.01
df = n1 + n2 – 2
n1 = 19
n2 = 27
df = 19 + 27 – 2 = 44
So, critical values by using t table are given as below:
Critical values = -2.6923 and 2.6923
Decision rule:
Reject null hypothesis H0 if test statistic t is not lies between -2.69 and 2.69, otherwise do not reject the null hypothesis H0.
Part b
Test statistic formula for pooled variance t test is given as below:
t = (X1bar – X2bar) / sqrt[Sp2*((1/n1)+(1/n2))]
Where Sp2 is pooled variance
Sp2 = [(n1 – 1)*S1^2 + (n2 – 1)*S2^2]/(n1 + n2 – 2)
n1 = 19
n2 = 27
X1bar = 160000
X2bar = 181000
S1 = 37000
S2 = 32000
Sp2 = [(n1 – 1)*S1^2 + (n2 – 1)*S2^2]/(n1 + n2 – 2)
Sp2 = [(19 – 1)* 37000^2 + (27 – 1)* 32000^2]/(19 + 27 – 2)
Sp2 = 1165136363.6364
t = (X1bar – X2bar) / sqrt[Sp2*((1/n1)+(1/n2))]
t = (160000 – 181000) / sqrt[1165136363.6364*((1/19)+(1/27))]
t = -21000 / 10221.3583
t = -2.0545
Test statistic = -2.05
Part c
Here, test statistic value is lies between the critical values -2.69 and 2.69, so we do not reject the null hypothesis H0
Fairfield cannot conclude that the population means are different.