The main purpose of the research is to explore the educational assessment on the basis of Evidence-Centered Design（ECD） to build a convenient and effective diagnosis system. We use Bayesian networks for modeling assessment data and identifying bugs and sub-skills in The “Fraction And Decimal” of Mathematics in Grade 6. This research integrates the opinion of the experts, scholars, and primary school teachers. Also, The multimedia computer is devised for diagnostic testing and computerizes adaptive remedial instruction with the system. Students can receive not only individual diagnostic tests but adequate and in-time computerized adaptive remedial instruction. Evaluation Diagnosis and remedy can be achieved simultaneously. The results： 1.The Bayesian networks evaluation mode and evidence-centered assessment design apply effectively to the diagnosis of students’ mistakes and sub-skills. 2.To set up a complete and effective Bayesian network. one has to do some research to build a Bayesian networks at first and then modifies it by analyzing practical materials. 3.Both testing and remedial teaching can be achieved simultaneously. 4.The progress of students is significant after taking the Computerize adaptive remedial instruction.
