Question

A hypothesis test is to be performed to compare the means of two populations, using a paired sample. The sample of 15 paired differences contains an outlier but otherwise is roughly bell-shaped. Assuming that it is not legitimate to remove the outlier, which test is better to use-the paired t-test or the paired Wilcoxon signed-rank test? Explain your answer,

Short answer

The paired Wilcoxon signed-rank test is preferable to the paired$t$-test.

Step-by-step solution

Given Information

The sample of $15$paired differences contains an outlier but otherwise is roughly bell-shaped .

We have to explain the test which is better for the given conditions.

Explanation: Step 2

A sample of $15$paired differences was clearly picked in the current situation, and the difference distribution is substantially bell-shaped with an outlier. Because an outlier is impossible to eliminate.