Welcome to CSCAR's treatment assignment system.

Background: CSCAR's sequential treatment assignment system is intended to assist researchers who are conducting trials in which subjects are assigned sequentially to treatment groups. It aims to provide treatment assignments that are balanced across the levels of one or more pre-treatment covariates. Sequential assignment is useful whenever a complete list of all research subjects is not available at the beginning of a trial. It is especially effective when a study will enroll a small or moderate number of subjects.

Methodology: This system implements an approach to treatment assignment using minimization that was developed by Pocock and Simon (Biometrics 31, 1975). The minimization approach reduces covariate imbalances by utilizing non-uniform assignment probabilities for the different treatment groups, in order to reduce the level of imbalance following each round of treatment assignment. Although the probabilities are not uniform, the treatment assignments are still random, which reduces the risk that a user can bias the results of the trial by selectively enrolling patients.

Security: This system identifies users through their Google account id. Users must be signed into their Google account whenever using the system. This system runs on Google AppEngine and the data are stored on Google's servers. You will be given the option to store either complete data or aggregated data for the subjects in your study. In the latter case, only the frequency distribution of each covariate within each treatment group is retained by the system.

Enter the CSCAR treatment assignment system