Research

Forecast Encompassing Tests for the Expected Shortfall (with Timo Dimitriadis) -  International Journal of Forecasting (2021), Volume 37, Issue 2   published version

We introduce new forecast encompassing tests for the risk measure Expected Shortfall (ES). The ES currently receives much attention through its introduction into the Basel III Accords, which stipulate its use as the primary market risk measure for the international banking regulation. We utilize joint loss functions for the pair ES and Value at Risk to set up three ES encompassing test variants. The tests are built on misspecification robust asymptotic theory and we investigate the finite sample properties of the tests in an extensive simulation study. We use the encompassing tests to illustrate the potential of forecast combination methods for different financial assets.

Sparsity-induced identification of factor-augmented VAR models (with Maurizio Daniele)    current version     Supplement    Online Supplement 

This paper introduces a regularized factor-augmented vector autoregressive (RFAVAR) model which incorporates sparsity in the factor loadings. Within this framework, the factors can load on a subset of variables, thereby enabling factor identification and enhancing their economic interpretation. The proposed RFAVAR model allows to investigate the effects of structural shocks on economically interpretable factors and on all observed time series included in the model. We prove consistency for the estimators of the factor loadings, the covariance matrix of the idiosyncratic component, the factors, and the autoregressive parameters in the dynamic model. In an empirical application, we examine the effects of a monetary policy shock on a broad range of economically relevant variables. The identification of this shock is accomplished through a joint identification of the factor model and the structural innovations in the VAR model. The obtained impulse response functions align with the established economic rationale.

Empirical Asset Pricing in a DGSE Framework - Reconciling Calibration and Econometrics using Partial Indirect Inference (with Joachim Grammig and Dalia Elshiaty) current version

This paper aims at a critical assessment of the DSGE asset pricing approach. By employing partial indirect inference, we acknowledge that parts of a model are misspecified, while others retain the claim to capture economic reality, namely the ability to price assets traded in real markets. Consequently, we use binding functions that facilitate the consistent estimation of the structural model parameters of interest (concerning investor preferences), while treating others (governing macroeconomic dynamics) as nuisance parameters that are calibrated. The results of our empirical analysis are not unfavorable for the DSGE asset pricing approach, but they also indicate that the very positive interpretation of calibration results, in particular regarding the resolution of asset pricing puzzles, should be taken with a grain of salt.

Encompassing Tests for Value at Risk and Expected Shortfall Multi-Step Forecasts based on Inference on the Boundary (with Timo Dimitriadis and Xiaochun Liu) - Journal of Financial Econometrics, Volume 21, Issue 2, Spring 2023, Pages 412–444   published version

We propose forecast encompassing tests for the Expected Shortfall (ES) jointly with the Value at Risk (VaR) based on flexible link (or combination) functions. Our setup allows testing encompassing for convex forecast combinations and for link functions which preclude crossings of the combined VaR and ES forecasts. As the tests based on these link functions involve parameters which are on the boundary of the parameter space under the null hypothesis, we derive and base our tests on nonstandard asymptotic theory on the boundary. Our simulation study shows that the encompassing tests based on our new link functions outperform tests based on unrestricted linear link functions for one-step and multi-step forecasts. We further illustrate the potential of the proposed tests in a real data analysis for forecasting VaR and ES of the S&P 500 index. 

Penalized QMLE and model selection of time series regressions (with Sébastien Laurent (AMSE) and Christian Francq (CREST))

We examine a linear regression model applied to the components of a time series, aiming to identify time-varying, constant as well as zero conditional beta coefficients. To address the non-identifiability of parameters when a conditional beta is constant, we employ a Lasso-type estimator. This penalized estimator simplifies the model by shrinking the estimates in favor of natural constant beta representations. We propose a multistep estimator that first captures the dynamics of the regressors before estimating the dynamics of the betas. This strategy breaks down a large-dimensional optimization problem into several lower-dimensional ones. Since we avoid making strict parametric assumptions about the innovation distributions, we use quasi-maximum likelihood estimators. The non-Markovian nature of the global model means that standard convex optimization results cannot be applied. We analyze the asymptotic distribution of the multistep Lasso estimator and its adaptive version, deriving bounds on the maximum value of the penalty term. We also propose a nonlinear coordinate-wise descent algorithm, which is demonstrated to find stationary points of the objective function. The finite-sample properties of these estimators are further explored through a Monte Carlo simulation and illustrated with an application to financial data.