Quantifying Model Estimation Risk: A simple analytical approach

Cover Image

In derivatives markets, underlying asset price models are commonly calibrated to market quotes of liquid options by minimizing an error functional.

May 4, 2023 | 5:00 - 6:00 PM | Babbio 2nd FL Room 219

In derivatives markets, underlying asset price models are commonly calibrated to market quotes of liquid options by minimizing an error functional. Calibration risk is associated with the error in the estimation of the driving model parameters, which is conveyed to the final statistical product, such as, for example, the price of other illiquid financial contracts. We present a simple, yet efficient and intuitive framework for gauging the estimation error based on asymptotic results and explain how we can improve this and the reliability of parameter estimates. We conduct an empirical study in relation to various popular models (lognormal, jump diffusions, stochastic volatility models with or without price jumps) calibrated to observed market quantities. We investigate the implications for model outputs (such as ultimate derivative contract prices) and identify the main sources of uncertainty in the model output with respect to the uncertainty in the model parameters. Our results represent important news for market participants concerned about the uncertainty of the supposedly fair price of a contract.


Ioannis Kyriakou Picture

Ioannis works in quantitative methods on both the development of numerical techniques and applications in the fields of operations research and management science, finance, actuarial science and sector studies, including derivatives, risk management, shipping, commodities, pension product design and communication, stock returns forecasting and machine learning. His recent research contributions have appeared in Operations Research, the European Journal of Operational Research, Mathematics of Operations Research, Tourism Management, Transportation Research Parts A and E, Review of Finance, European Financial Management, and others. He is currently Associate Editor of the International Journal of Finance & Economics, Annals of Actuarial Science and member of the management chair committee of the Quantitative Finance and Risk Analysis (QFRA) Symposium. He is the Director of the world-renowned MSc in Actuarial Science and MSc in Actuarial Management of Bayes Business School (formerly Cass). In addition to his work at City, he has been a visiting professor at the Università del Piemonte Orientale and an affiliate faculty at Cyprus International Institute of Management. Previously he worked for Lloyd’s Treasury and Investment Management. Ioannis obtained his PhD in Finance from City, following his MSc in Risk and Stochastics from LSE with distinction, and his first-class BSc (Hons) degree in Actuarial Science from City. He holds the Diploma in Actuarial Techniques, is an affiliate member of the Institute and Faculty of Actuaries and acts as an independent examiner at several universities.