Abstract: For reducing the amount of fault sample size during the testability demonstration test with specified risk level, and by taking FDR as the target, a new method is presented to make full use of the testability test data acquired in the development stage. Firstly, the conventional statistics test model is given, and then, a method is put forward for processing the data acquired in the development stage. Using the probability of Beta function, the confidence lower limit of FDR is transferred into lower percentile of Beta distribution. A coefficient is introduced to reflect the difference between FDR acquired by development stage data and the required FDR level, finally, the integrated test scheme is determined by the required FDR confidence level distribution function considering the risk level. The integrated test scheme can reduce the necessary fault sample size and then reduce the risk level.

Key words: Beta distribution, Confidence probability function, Difference factor, Fault sample size, Risk level, Testability demonstration test