Many robust analogs of the classic analysis of covariance method have been proposed. One approach, when comparing two independent groups, uses selected design points and then compares the groups at each design point using some robust method for comparing measures of location. So, if K design points are of interest, K tests are performed. There are rather obvious ways of performing, instead, an omnibus test that for all K points, no differences between the groups exist. One of the main results here is that several variations of these methods can perform very poorly in simulations. An alternative approach, based in part on the usual sample median, is suggested and found to perform reasonably well in simulations. It is noted that when using other robust measures of location, the method can be unsatisfactory.
Wilcox, Rand R.
"ANCOVA: A Robust Omnibus Test Based On Selected Design Points,"
Journal of Modern Applied Statistical Methods:
1, Article 3.
Available at: http://digitalcommons.wayne.edu/jmasm/vol5/iss1/3