Integral estimate method for censored data

An integral estimate method for censored data or incomplete data of valuable products is presented. Combining the results of simulation or digital design and censored data or incomplete data, it can totally infer the censored data or the incomplete data in multi-state (for multi-population). And then, in each state, it can derive the estimators of the location and the scale parameter, and the confidence limits and intervals of population percentiles. Compared with traditional method, this presented method not only has higher precision but also solves the problem of reliability assessment with very small sample. Another method is also presented, which can test the results of simulation or digital design with censored data or incomplete data.