Dynamic Model Averaging for Practitioners in Economics and Finance: The eDMA Package

Raftery, Kárnỳ, and Ettler (2010) introduce an estimation technique called Dynamic Model Averaging (DMA). In their application, DMA is used to the problem of predicting the output strip thickness for a cold rolling mill, where the output is measured with a time delay. Recently, DMA has also shown to be very useful in macroeconomic and financial applications. In this paper, we present the eDMA package for DMA estimation in R, which is especially suited for practitioners in economics and finance. Our implementation proves to be up to 133 times faster then a standard implementation on a single–core CPU. Using our package, practitioners are able perform DMA on a standard PC without needing to resort to clusters with large memory. We demonstrate the usefulness of this package through some simulation experiments and an empirical application using quarterly inflation data.