Some extensions of Langenberg model for clinical trials with delayed observations normally distributed responses

Langenberg and Srinivasan [1981. On the Colton model for clinical trials with delayed observations normally distributed responses. Biometrics 37, 143–148.] proposed two simple procedures for analyzing data from patients who arrive during the waiting period, caused by the lag, between the trial and treatment stages of the model. The relative performance of the procedures in the Bayesian framework is discussed when the responses to two treatments are normally distributed with unknown means and a common known variance. A generalization of the Langenberg and Srinivasan formulation of the two procedures to an arbitrary finite number of populations is proposed. Results for the special case of two populations, one of them known, are presented.