1. In one-way analysis of variance tests, do larger test statistics result in larger P-values, smaller P-values, or P-values that are unrelated to the value of the test statistic?
2. What are the advantages and disadvantages of nonparametric tests?
3. Why is the sign test considered to be a "nonparametric" test of a "distribution-free" test?
4. Assume that matched pairs of data result in the given number of signs when the value of the second variable is subtracted from the corresponding value of the first variable. Use the sign test with a 0.05 significance level to test the null hypothesis of no difference.
Positive signs: 13; negative signs: 1; ties: 0 (from a preliminary test of the MicroSort method of gender selection)
Positive signs: 5; negative signs: 7; ties: 1 (from a class project testing for the difference between reported and measured heights of males)