Course Details

<b>Learning objectives</b><br> The goal of this course is to introduce students to advanced econometric methods for time series data in financial applications.<br> <b>Content</b><br> The course focuses on the Generalized Method of Moment (GMM) and nonparametric methods, and considers estimation and inference for asset pricing and derivative pricing models. The first part of the course is concerned with the GMM. The GMM has been introduced in Hansen (1982) and Hansen, Singleton (1982) to estimate a structural parameter defined by moment restrictions. In economic applications, moment restrictions are typically deduced from the Euler conditions implied by expected utility maximization or, more generally, the no-arbitrage principle. In this course we investigate the implementation and the large sample properties of GMM with serially dependent data. We address the key issues of consistent estimation of the variance-covariance matrix of the GMM estimator and optimal choice of the weighting matrix.<br> Nonparametric methods are the subject of the second part of the course. Nonparametric methods are appealing for empirical economic analysis since they dispense the researcher from introducing restrictive parametric assumptions, that have no justification in economic or financial theory. The course focuses on the most commonly used nonparametric method in economics, that is the kernel based approach. We consider kernel estimators of density functions, regression functions and their derivatives, with time series data. We investigate the large sample properties of kernel estimators, and we address the issue of the choice of the bandwidth parameter.<br> There exists an important literature in finance on applications of GMM and nonparametric methods for asset pricing purposes. In the last part of the course we consider GMM estimation of asset pricing models in either preference-based, or no-arbitrage, modeling frameworks. We also review recent applications of nonparametric methods for estimation of risk-neutral densities and derivative pricing. The literatures on GMM estimation and nonparametric analysis find a point of contact in the so-called information-based approach to GMM. In this area, the course introduces the Extended Method of Moments (XMM), which is a new information-based estimator of option prices using time series data on spot prices and cross-sectional data on derivatives, and the conditional Hansen-Jagannathan distance for comparing possibly misspecified conditional asset pricing models.<br> <b>General information</b><br> Please see <a href="https://www.unisg.ch/en/studying/exchange-programme/incoming-guest-students/guest-auditors-and-individual-course-participation/">this website</a> for information on how to participate in the course. Please write to <a href="mailto:phd@unisg.ch">phd@unisg.ch</a> by <b>September 7, 2025</b> and request the form that is needed to register for an individual course participation at the doctoral level.