Suppose That You Want to Perform a Hypothesis Test to Compare

Suppose that you want to perform a hypothesis test to compare the means of two populations using a paired sample. Preliminary data analyses of the sample of paired differences suggest that the distribution of the paired-difference variable is skewed to the right . The sample of 20 paired differences contains an outlier. If it is not legitimate to remove the outlier, is it reasonable to use a paired t-test? Is it reasonable to use a paired Wilcoxon signed-rank test? Explain your thinking