The Behavioral and Experimental Economics group has an influential position in this field in the Netherlands and Europe. CREED, the Amsterdam-based group, focuses particularly on three main projects: economics of political decision making; bounded rationality and institutions and experimental economics. The research of the Rotterdam-based group focuses on two broad themes: decision under risk and uncertainty and intertemporal choice.
- S. J. Koopman, A. Lucas, M. Scharth
- firstname.lastname@example.org; email@example.com
- The Review of Economics and Statistics, 2016, 98, 97-110
We verify whether parameter-driven and observation-driven classes of dynamic models can outperform each other in predicting time-varying parameters. We consider existing and new dynamic models for counts and durations, but also for volatility, intensity, and dependence parameters. In an extended Monte Carlo study, we present evidence that observation-driven models based on the score of the predictive likelihood function have similar predictive accuracy compared to their correctly specified parameter-driven counterparts. Dynamic observation-driven models based on predictive score updating outperform models based on conditional moments updating. Our main findings are supported by the results from an extensive empirical study in volatility forecasting.
To read the article click here.