Econometrics Seminar Series. "Robust Estimation in Conditional Moment Models with Time-Varying Parameters" (Joint Work with Farhad Shahryarpoor)
Published: 27 February 2025
21 March 2025. Professor Bertille Antoine, Simon Fraser University
Professor Bertille Antoine, Simon Fraser University
"Robust Estimation in Conditional Moment Models with Time-Varying Parameters" (Joint Work with Farhad Shahryarpoor)
Friday, 21 March 2025. 15:00-16:30
Room 141B, Adam Smith Business School Building
Abstract
In a parametric conditional moment model with time-varying parameters, we develop a new integrated conditional moment (ICM) estimator which uses all information from conditional restrictions seamlessly. Our approach builds on the ICM principle originally proposed by Bierens (1982) and combines it with local smoothing to deliver estimates of the time-varying parameters. Under general regularity conditions - including local stationarity and restrictions on plysical dependence - we show that our estimator is consistent and asymptotically normally distributed. Importantly, our approach is a one-step approach that is robust to parametrizing - and estimating - the relationship between endogenous variables and instruments. Our simulation study document the reliability and power of our approach in a variety of cases - and, especially, when the underlying relationship between the endogenous variables and the instruments cannot be reliably estimated - even with flexible time-varying approaches. Our estimation of the traditional Phillips curve that links inflation to unemployment with US data from 1960 to 2024 reveals important fluctuations over time, including the diminishing importance of unemployment, especially after 2006.
Bio
Bertille Antoine [Professor, Economics Department, Simon Fraser University, Research Fellow CMFE] is a specialist in econometrics. Her current research covers econometric issues arising in economic models that may not be well-identified, well-specified, or stable over time, with a focus on: asymptotic efficiency of inference methods (such as the generalized method of moments, as well as other minimum distance estimation methods and simulation-based matching inference), structural instability, robustness against poor identification, and robustness against misspecification. These contributions – although theoretically oriented – have had impact in several fields in economics and have led to better applied econometric practice: this includes empirical research in asset pricing, inflation and the macro-economy. Earlier work also covers issues related to estimation uncertainty and estimation risk in the context of portfolio choice.
For further information, please contact business-seminar-series@glasgow.ac.uk.
We foster a positive and productive environment for seminars through our Code of conduct.
First published: 27 February 2025