The validity of inferences based on incomplete observations in disease state models.

In many survival time studies or studies on the progression of a disease, information is often incomplete in the sense that it is known only that a patient has been in certain disease states at several time points. In this paper, conditions concerning the interrelationship between the disease process and the examination scheme (i.e., the pattern of examination times) are derived under which a valid statistical inference is possible. These conditions are confronted with examination schemes that are of practical importance in clinical research. A cancer marker study is used as an example to estimate the magnitude of the potential bias when the conditions derived are violated.