Structural Modeling and Forecasting Using a Cluster of Dynamic Factor Models (with C.Glocker)
We propose a modeling approach involving a series of small-scale dynamic factor models. They are connected to each other within a cluster, whose linkages are derived from Granger-causality tests. This approach merges the benefits of large-scale macroeconomic and small-scale factor models, rendering our Cluster of Dynamic Factor Models (CDFM) useful for model-consistent nowcasting and forecasting on a larger scale. While the CDFM has a simple structure and is easy to replicate, its forecasts are more precise than those of a wide range of competing models and those of professional forecasters. Moreover, the CDFM allows forecasters to introduce their own judgment and hence produce conditional forecasts.
Estimating the Probability of Acting as a Trustee (with D.Stadelmann)
We discuss a binomial mixture model for estimating the probability of a political representative acting as a delegate or a trustee. The model also returns the probability of congruence of a representative with the national median voter. The estimated probability of congruence strongly correlates with the observed frequency of congruence, which was obtained by matching parliamentary roll-call votes with the will of the median voter revealed in Swiss national referendums on identical legislative proposals. Since our method uses the roll-call votes of political representatives as sole input, it can be used to infer congruence levels of politicians, even if the will of the median voter is unobserved.