Question: A stock market analyst wants to test whether there are higher-than-usual returns on stocks following a two-for-one split. A random sample of 10 stocks that recently split is available. For each stock, the analyst records the percentage return during the month preceding the split and the percentage return for the month following the split. The data are

Before split (%):     0.5, 20.2, 0.9, 1.1, 20.7, 1.5, 2.0, 1.3, 1.6, 2.1

After split (%):       1.1, 0.3, 1.2, 1.9, -0.2, 1.4, 1.8, 1.8, 2.4, 2.2

Is there evidence that a stock split causes excess returns for the month following the split? Redo the problem, using the sign test. Compare the results of the sign test with those of the Wilcoxon test.