On parallelism of regression lines

Abstract

Testing of parallelism of regression lines is discussed and the
classical F-test is compared with the Sen rank test by means of simulations.
A rank based multiple comparisons rule for detecting regression lines with
different slopes is constructed and asymptotic distribution of the underlying
statistic is derived. This rule is compared by means of simulations with the
rule derived from the asumption that the random fluctuations are Gaussian.