Here again is the data on expense ratio (%) for a sample of 20 large-cap blended mutual funds introduced in Exercise 1.53:

1.03 1.23 1.10 1.64 1.30 1.27 1.25

.78 1.05 .64 .94 .86 1.05 .75

.09 0.79 1.61 1.26 .93 .84 A normal probability plot shows a distinctly nonlinear pattern, primarily because of the single outlier on each end of the data.

But a dotplot and boxplot exhibit a reasonable amount of symmetry. Assuming a symmetric population distribution, does the data provide compelling evidence for concluding that the population mean expense ratio exceeds 1%? Use the Wilcoxon test at significance level .1. [Note: The mean expense ratio for the population of all 825 such funds is actually 1.08.]