Conducting Mann-Whitney U (Wilcoxon rank sum) Tests in Stata
Mann-Whitney U Tests are an option for when typical t-tests can't be used. Before you run one, learn more about the theory behind it. They do not require anything special from your data, just that there are two groups (therefore a grouping variable) and a dependent variable.
The basic syntax is
ranksum [depvar], by ([grouping var])
ranksum happy, by(gender)and would produce the following output:
The output gives us a handy table displaying the two groups, their Ns (number of observations), the observed ranked sums and the rank sum that would be expected if the null hypothesis were retained (if there were no difference). Tied ranks can be an issue, so below the table there is a variance adjustment to account for these ties. Then we are reminded of the null hypothesis, and given the z-statistic and p-value.