The Essentials of Biostatistics for Physicians, Nurses, and Clinicians

154 CHAPTER 9 Nonparametric Methods

9.6 EXERCISES

1. Table 9.5 provides a modifi cation of the pig blood loss data as an exercise
   for the Wilcoxon rank - sum test
   Do the results differ from the standard two - sample t - test using pooled
   variances? Are the resulting p - values similar? Compare the t - test and the
   Wilcoxon rank - sum test for a one - side alternative that the treatment group
   has a lower blood loss average than the control group.


2. Apply the Wilcoxon rank - sum test to the data in Table 9.6 on the relation-
   ship between the number of patients with schizophrenia and the season of
   their birth by calling fall and winter as group 1, and spring and summer as
   group 2. The four individual seasons represent data points for each group.
   Ignore the possibility of a year effect.
   Do we need to assume that births are uniformly distributed? If we knew
   that there were a higher percentage of births in the winter months, how
   would that affect the conclusion?


3. Based on Table 9.7 , which is a modifi cation of the temperature data for
   New York and Washington, apply the sign test to see if the difference in
   the temperatures is signifi cant.


4. Using the data from Table 9.7 in exercise 3, compute the Spearman rank
   correlation coeffi cient between the two cities

Table 9.5

Pig Blood Loss Data (Modifi ed)

Control group pigs Treatment group pigs

786 643

375 666

3446 555

1886 823

465 1816

580 997

434 2828

3964 1351

2181 902

3237 1278

Sample mean = 1785.40 Sample mean = 1185.90