In: Statistics and Probability
Using the data from the previous question on LDL cholesterol, you decide to test if the variance in LDL cholesterol of patients admitted to the hospital with a heart attack is the same as that of those who have not (the control). You use the R function var.test and obtain the following output.
F test to compare two variances
data: ldl.ha and ldl.cont
F = 7.683, num df = 9, denom df = 15,
p-value = 0.0006501
alternative hypothesis: true ratio of
variances is not equal to 1
95 percent confidence interval:
2.460444 28.960945
sample estimates:
ratio of variances
7.683258
What is your decision and conclusion (with respect to variation in
LDL cholesterol levels) from the above R test output assuming an
alpha level of 0.05? AND how does this help us beyond this test of
the variance?
We want to test that the he variance in LDL cholesterol of patients admitted to the hospital with a heart attack is the same as that of those who have not (the control).
Ho:- The variance in LDL cholesterol of patients admitted to the hospital with a heart attack is the same as that of those who have not (the control).
Vs
Ha:- The variance in LDL cholesterol of patients admitted to the hospital with a heart attack is different from those who have not (the control)
Here from output decision based on P-value.
Alpha = level of significance = 0.05
P-value = 0.0006501
Reject Ho if P-value < alpha
Here p-value = 0.0006501 < alpha = 0.05
So we reject Ho
So we conclude that the The variance in LDL cholesterol of patients admitted to the hospital with a heart attack is different from those who have not (the control)
So variances are unequal.
This decision can be used in testing of difference between the two population means where we want to know that population variances are equal or not.