Abstract
In medical research, sequences of treatments may need to be applied to subjects over a period of time. Cross-over designs, in such cases, form a useful class for application. However, there may be some additional factor of variation embedded into the subjects, or the required constraints for application of a balanced design, (which is preferred), may not always be available and the cross-over designs may need to be conducted in parts or sessions. Nested cross-over designs are required under such conditions. Some such situations are considered here and useful nested cross-over designs are constructed. Relevant theory on modeling the observations obtained from such designs is also provided.
Get full access to this article
View all access options for this article.
