Estimation of FAVAR Models for Incomplete Data with a Kalman Filter for Factors with Observable Components

This article extends the Factor-Augmented Vector Autoregression Model (FAVAR) to mixed-frequency and incomplete panel data. Within the scope of a fully parametric two-step approach, the alternating application of two expectation-maximization algorithms jointly estimates model parameters and missing data. In contrast to the existing literature, we do not require observable factor components to be part of the panel data. For this purpose, we modify the Kalman Filter for factors consisting of latent and observed components, which significantly improves the reconstruction of latent factors according to the performed simulation study. To identify model parameters uniquely, the loadings matrix is constrained. In our empirical application, the presented framework analyzes US data for measuring the effects of the monetary policy on the real economy and financial markets. Here, the consequences for the quarterly Gross Domestic Product (GDP) growth rates are of particular importance.

Unexpected diversity within the extinct elephant birds (Aves: Aepyornithidae) and a new identity for the world's largest bird

Madagascar's now-extinct radiation of large-bodied ratites, the elephant birds (Aepyornithidae), has been subject to little modern research compared to the island's mammalian megafauna and other Late Quaternary giant birds. The family's convoluted and conflicting taxonomic history has hindered accurate interpretation of morphological diversity and has restricted modern research into their evolutionary history, biogeography and ecology. We present a new quantitative analysis of patterns of morphological diversity of aepyornithid skeletal elements, including material from all major global collections of aepyornithid skeletal remains, and constituting the first taxonomic reassessment of the family for over 50 years. Linear morphometric data collected from appendicular limb elements, and including nearly all type specimens, were examined using multivariate cluster analysis and the Bayesian information criterion, and with estimation of missing data using multiple imputation and expectation maximization algorithms. These analyses recover three distinct skeletal morphotypes within the Aepyornithidae. Two of these morphotypes are associated with the type specimens of the existing genera Mullerornis and Aepyornis , and represent small-bodied and medium-bodied aepyornithids, respectively. Aepyornis contains two distinct morphometric subgroups, which are identified as the largely allopatric species A. hildebrandti and A. maximus. The third morphotype, which has not previously been recognized as a distinct genus, is described as the novel taxon Vorombe titan . Vorombe represents the largest-bodied aepyornithid and is the world's largest bird, with a mean body mass of almost 650 kg. This new taxonomic framework for the Aepyornithidae provides an important new baseline for future studies of avian evolution and the Quaternary ecology of Madagascar.