Answers are grounded in this paper and cite their sources.
Demonstrates relationships between sample sizes and error ranges in capital modeling, indicating significant implications for risk assessment.
Capital modeling requires very large samples. We use the normal approximation to derive relationships between sample sizes and error ranges for estimating value at risk and tail value at risk. We focus on one-year capital models. In a one-year model, investments and catastrophes are the greatest risk sources. We show how the shape and tail behavior of their probability distributions lead to different requirements in sample sizes. Related mathematical theories are also reviewed. Address for Correspondence: yingjie_zhang@cinfin.com
No takes yet. Share an insight, caveat, or question.
Yingjie Zhang (2022) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: