In: Statistics and Probability
A random sample of n1 = 22 summer days in Los Angeles gave a sample mean pollution index of x-bar1 = 49. Previous studies show that σ1 = 12. For San Francisco, a random sample of n2 = 17 summer days gave a sample mean pollution index of x-bar2 = 45. Previous studies show that σ2 = 15. Assume the pollution index is normally distributed. Do these data indicate the mean population pollution index of Los Angeles is greater than San Francisco? Use a 1% level of significance.
Show all work and calculations.
Solution:
Here, we have to use two sample z test for the difference between two population means.
The null and alternative hypotheses for this test are given as below:
Null hypothesis: H0: the mean population pollution index of Los Angeles is same as that of San Francisco.
Alternative hypothesis: Ha: the mean population pollution index of Los Angeles is greater than San Francisco.
H0: µ1 = µ2 versus Ha: µ1 > µ2
This is an upper tailed test.
We are given
Level of significance = α = 0.01
The test statistic formula for this test is given as below:
Z = (X1bar – X2bar) / sqrt[(σ12 / n1)+(σ22 / n2)]
From given data, we have
X1bar = 49
X2bar = 45
σ1 = 12
σ2 = 15
n1= 22
n2= 17
X1bar – X2bar = 49 - 45 = 4
Z = (X1bar – X2bar) / sqrt[(σ12 / n1)+(σ22 / n2)]
Z = 4 / sqrt[(12^2 / 22)+( 15^2 / 17)]
Z = 4/4.4476
Z = 0.8994
Test statistic = Z = 0.8994
Critical value = 2.3263
(by using z-table)
P-value = 0.1842
(by using z-table)
P-value > α = 0.01
So, we do not reject the null hypothesis
There is not sufficient evidence to conclude that the mean population pollution index of Los Angeles is greater than San Francisco.