Abstract

It is now well established in case-control studies with individual matching that the statistical analysis must take the fact of individual matching into account. The problems of so doing have been thoroughly dealt with for the situation of the factor of interest being a two-level factor (all-or-none response) and with one or more matched controls per patient. These results are extended in this paper to the situation where the factor can assume multiple levels in studies where each patient is matched with a single control.