__smbhome.uscs.susx.ac.uk_tjk30_Documents_EJOR2017_accepted_manuscript.pdf (656.44 kB)
An improved least squares Monte Carlo valuation method based on heteroscedasticity
journal contribution
posted on 2023-06-09, 20:21 authored by Frank J Fabozzi, Tommaso Paletta, Radu TunaruRadu TunaruLongstaff–Schwartz’s least squares Monte Carlo method is one of the most applied numerical methods for pricing American-style derivatives. We examine the algorithms regression step, demonstrating that the OLS regression is not the best linear unbiased estimator because of heteroscedasticity. We prove the existence of heteroscedasticity for single-asset and multi-asset payoffs numerically and theoretically, and propose weighted-least squares MC valuation method to correct for it. An extensive numerical study shows that the proposed method produces significantly smaller pricing bias than the Longstaff–Schwartz method under several well-known price dynamics. An empirical pricing exercise using market data confirms the advantages of the improved method.
History
Publication status
- Published
File Version
- Accepted version
Journal
European Journal of Operational ResearchISSN
0377-2217Publisher
ElsevierExternal DOI
Issue
2Volume
263Page range
698-706Department affiliated with
- Accounting and Finance Publications
Research groups affiliated with
- Quantitative International Finance Network Publications
Full text available
- Yes
Peer reviewed?
- Yes