In: Statistics and Probability
Business Majors Non-Business Majors
n1 = 8 n2 = 5
_ _
X1 = 545 X2 = 525
s1 = 120 s2 = 60
b. Using a 0.05 level of significance, test the clam that average GMAT scores for business majors is above the average GMAT scores for non-business majors in the population. Assume unequal population variances.
Part a
Here, we have to use the F test for the population variances.
H0: σ12 = σ22 versus Ha: σ12 ≠ σ22
(Two tailed test)
We are given
α = 0.05
S1 = 120
S2 = 60
n1 = 8
n2 = 5
df1 = n1 – 1 = 8 – 1 = 7
df2 = n2 – 1 = 5 – 1 = 4
Test statistic is given as below:
F = S1^2/S2^2 = 120^2/60^2 = 4
P-value = 0.1984
(by using F-table or excel)
P-value > α = 0.05
So, we do not reject the null hypothesis
There is sufficient evidence to conclude that the population variances are equal.
Part b
Solution:
Here, we have to use two sample t test for the difference in population means by assuming unequal population variances.
H0: µ1 = µ2 versus Ha: µ1 > µ2
t = (X1bar – X2bar) / sqrt[(S12 / n1)+(S22 / n2)]
Degrees of freedom = [(S12/n1) + (S22/n2)]^2 / [((S12/n1)^2/(n1 – 1)) + ((S22/n2)^2/(n2 – 1))]
WE are given
We are given
α = 0.05
X1bar = 545
X2bar = 525
S1 = 120
S2 = 60
n1 = 8
n2 = 5
Degrees of freedom = [(120^2/8) + (60^2/5)]^2 / [((120^2/8)^2/(8 – 1)) + ((60^2/5)^2/(5 – 1))]
Degrees of freedom = 10.7188
Degrees of freedom = 10
t = (X1bar – X2bar) / sqrt[(S12 / n1)+(S22 / n2)]
t = (545 – 525) / sqrt[(120^2 / 8)+(60^2 / 5)]
t = 20/50.1996
t = 0.3984
P-value = 0.3494
(by using t-table)
P-value > α = 0.05
So, we do not reject the null hypothesis
There is insufficient evidence to conclude that that average GMAT scores for business majors is above the average GMAT scores for non-business majors in the population.