Statistical Resampling in Assessing External Threats to Structures

摘要

The paper deals with an application of bootstrap methods to estimating risk to structures posed by extreme, dangerous phenomena. It is considered how to calculate risk values when a limited amount of data on actions imposed by these phenomena is available. The paper presents a procedure allowing applying this limited data to calculating bootstrap confidence intervals for probabilities of damage which can be caused by the actions. It is discussed how to incorporate the confidence intervals in an expression of the risk.