The principal topic covered in this paper is the development of a test of the hypothesis that two regression lines are parallel under the conditions that the two sets of error terms are normally distributed but with (possibly) different variances. An incidental topic which is covered concerns a test for the slope of a single regression line; no normality assumption is required for this second test. Both tests are analogous to the Wilcoxon test. The discussion in this paper is on a rather technical level; for a less technical discussion of the first test, see Research Bulletin 62-28.