In Example 12.2.4, there is a slightly simpler way to simulate a sample from the posterior distribution of x y. Suppose that we can

In Example 12.2.4, there is a slightly simpler way to simulate a sample from the posterior distribution of μx − μy. Suppose that we can simulate as many independent t pseudo-random variables as we wish with whatever degrees of freedom we want. Explain how we could use these t random variables to simulate a sample from the posterior distribution of μx − μy.