Abstract | ||
---|---|---|
AbstractThe need to estimate a function value from sample data at a point that is itself estimated from the same data set arises in many application settings. Such applications include value-at-risk, conditional value-at-risk, and other so-called distortion risk measures. In this note, Peter W. Glynn, Lin Fan, Michael C. Fu, Jian-Qiang Hu, and Yijie Peng provide a simple proof for a central limit theorem for such estimators, and provide an accompanying batching/sectioning methodology that can be used to construct large-sample confidence intervals in the presence of such estimators.We provide a simple proof of the central limit theorem (CLT) for estimated functions at estimated points. Such estimators arise in a number of different simulation-based computational settings. We illustrate the methodology via applications to quantile estimation and related sensitivity analysis, as well as to computation of conditional value-at-risk. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1287/opre.2019.1922 | Periodicals |
Keywords | DocType | Volume |
simulation,central limit theorem | Journal | 68 |
Issue | ISSN | Citations |
5 | 0030-364X | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter W. Glynn | 1 | 1527 | 293.76 |
Lin Fan | 2 | 0 | 0.34 |
Michael C. Fu | 3 | 1161 | 128.16 |
Jian-Qiang Hu | 4 | 25 | 6.52 |
Yijie Peng | 5 | 32 | 12.59 |