Article ID: | iaor20082052 |
Country: | Netherlands |
Volume: | 35 |
Issue: | 2 |
Start Page Number: | 251 |
End Page Number: | 260 |
Publication Date: | Mar 2007 |
Journal: | Operations Research Letters |
Authors: | Juneja Sandeep, Zeevi Assaf, Bassamboo Achal |
This paper proves that there does not exist an asymptotically optimal state-independent change-of-measure for estimating the probability that a random walk with heavy-tailed increments exceeds a ‘high’ threshold before going below zero. Explicit bounds are given on the best asymptotic variance reduction that can be achieved by state-independent schemes.