The purpose of baseline correction in between-patient studies is to ensure that the two treatments groups are not statistically different at the beginning of the study. However, adjusting for baseline values is not an easy task and there is no unique way of doing it. One method is to treat the problem as longitudinal data and fit a cumulative logistics regression model. But this comes with the common burden of parametric assumptions which may not have any relevance to the data generating process. The other popular option is to resort to nonparametric techniques such as the Mann-Whitney-Wilcoxon test or Smirnov like tests. Each of these procedures invokes an artificial order in the ordinal data.
This is a major drawback of such procedures yielding false significance between categories which otherwise are not comparable. Also, the tests are dependent on the particular pseudo-ordering chosen to construct the test statistic, thus being highly sensitive to the order of the categories. We seek to overcome the aforementioned drawbacks of nonparametric baseline adjustment procedures. We propose a new method which adjusts for baseline without relying on any specific assumptions.
|