Abstract
The bootstrapping is a sophisticate statistical technique to duplicate the data itself by resampling the underlying population data, and enables us to investigate the statistical properties. It is useful to estimate standard errors and confidence intervals for complex estimators of complex parameters of the distribution from a small number of data. In this paper, we apply the bootstrapping techniques to the software release problems and propose the flexible decision making by taking account of uncertainty. More precisely, we derive interval estimates of the optimal software release times and their associated cost criteria. Based on the maximum likelihood estimation of parametric models such as the so-called exponential non-homogeneous Poisson process (NHPP) model, we assess the probability distributions of estimators of the optimal software release timing.