City Research Online

Incremental Volatility and Related Portfolio Analytics

Mignacca, D. & Fusai, G. ORCID: 0000-0001-9215-2586 (2022). Incremental Volatility and Related Portfolio Analytics. The Journal of Portfolio Management: the journal for investment professionals,

Abstract

In this note the authors prove a simple formula to compute the Incremental Volatility, i.e. the change in the portfolio volatility due to the removal of one asset from the portfolio. The common practice adopted in the literature and in the industry is to avoid the full recalculation of the portfolio volatility and to use a first order approximation based on the gradient of the portfolio volatility. Here, the authors introduce a new exact formula that does not require to recompute the volatility of the new portfolio, but exploits quantities computed previously. Using the new formula, they can easily compute the effect on the portfolio volatility of any arbitrary change in the weight of one asset as well as to determine the optimal trade, i.e. the weight change that allows the maximum reduction in the portfolio volatility. A simulation exercise and an empirical analysis illustrate the clear advantage, in terms of accuracy, saving in computational time and calculation of portfolio analytics, respect to the full re-evaluation and the commonly used linear approximation. Due to their striking simplicity, the new formulas provide important portfolio analytics of immediate use in the asset management industry.

Publication Type: Article
Additional Information: This article has been accepted for publication in The Journal of Portfolio Management: https://jpm.pm-research.com/. Published by Portfolio Management Research.
Publisher Keywords: Incremental Volatility, Marginal Volatility, Hot Spot, Best Hedge
Subjects: H Social Sciences > HG Finance
Departments: Bayes Business School > Finance
[img] Text - Accepted Version
This document is not freely accessible due to copyright restrictions.

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login