*TWO SAMPLE MEAN
TWO SAMPLE MEAN
The relationship between two variables may be:
Types of Data
Independent data
Paired Data
2 groups
1 Variable
1 group
2 variables
n1=n2
Independent
Paired
We test normality with the Shapiro-Wilk test. The null-hypothesis is that the sample comes from a Normal distribution. If the p-value is greater than the confidence level (alpha), we don't reject the hypothesis
If Normal:
We can apply the Independent samples t-test, as we have checked Normality and independence. This will provide us with information about the relationship between the means
If not Normal
We compute the Wilcoxon test for independent samples
We can now check the equality of the variances by means of t-tests for equal variances
First, we need to asses normality. Here, we have to check the normality of the difference of the two variables. For this we need to check the difference of the variables. To do this, we compute a new variable "dif" and compute the Shapiro-Wilk test
If Normal
We can Apply the Paired T-test
If not Normal
Wilcoxon test for paired samples