Estimating dynamic equilibrium models using mixed frequency macro and financial data

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. We provide a framework for inference in dynamic equilibrium models including financial market data at daily frequency, along with macro series at standard lower frequency. Our formulation of the macro-finance model in continuous-time conveniently accounts for the difference in observation frequency. We suggest the use of martingale estimating functions (MEF) to infer the structural parameters of the model directly through a nonlinear optimization scheme. This method is compared to regression-based methods and the general method of moments (GMM). We illustrate our approaches by estimating the AK-Vasicek model with mean-reverting interest rates. We provide Monte Carlo evidence on the small sample behavior of the estimators and report empirical estimates using 30 years of U.S. macro and financial data. Terms of use: Documents inJEL-Code: C130, E320, O400.

Structural analysis with mixed-frequency data: A model of US capital flows

“…In this paper, unlike in most existing work on mixed frequency models which focuses on forecasting, we examine the response of macroeconomic and financial variables to structural shocks identified relying on variables observed at different frequencies. In this sense, this paper complements the analysis by and Christensen, Posch, and van der Wel (2016) who emphasize the role of mixed frequency variables in DSGE models. To this end, following Ghysels (2016), we propose a mixed frequency VAR model, the MIDAS-VAR, that can be seen as a multivariate specification that encompasses both the unrestricted-MIDAS (U-MIDAS) model by Foroni, Marcellino, and Schumacher (2014) and the reverse unrestricted MIDAS (RU-MIDAS) model by Foroni, Guérin, and Marcellino (2015).…”

The Financial Accelerator Mechanism: Does Frequency Matter?

“…There is a group of papers interested in methodological issues and/or performing mixedfrequency estimation with the aim of evaluating the impact on estimated parameters as compared with a different (often quarterly) frequency. Christensen et al (2016) estimate a small general equilibrium (AK-Vasicek) model with both macro and financial data. Their focus is mostly methodological and related to the use of the martingale estimating functions.…”

Particle filtering, learning, and smoothing for mixed-frequency state-space models

“…Bai et al (2013) examined the relationship between MIDAS and Kalman filter. Christensen et al (2016) Mariano and Murasawa (2010), Qian (2016), Marcellino and Sivec (2016), Ghysels (2016), among many others. Foroni and Marcellino (2013) provide a survey for mixed-frequency treatment.…”