Abstract: Based on the analysis of loss distribution approach,loss events are divided into three types:internal fraud,external fraud and illegal operation.Then,we apply two-stage distribution to fit the loss intensity distribution of operational risk and use Gibbs sampling of Bayesian theory to obtain the parameter estimates,which can reduce error caused by the insufficient low-frequency and high-loss data.In view of the correlation between different types of operational risk loss,the copula function is applied to integrate the total loss distribution.Finally,we calculate VaR and CVaR for different confidence level of the operational risk of commercial banks in China.The empirical result shows that:Parameter estimation based on Bayesian theory takes into accounta priori information such as population and sample information which can reduce the estimated error.The introduced copula function and measured value of VaR and CV aR not only consider the pro bability of loss events,but also can calculate potential losses of operational risk,so it can get a more accurate measurement result of operational risk.

Key words: operational risk, bayesian sampling, loss distribution approach, copula