Institut für Volkswirtschaftslehre

Permanent URI for this collectionhttps://hohpublica.uni-hohenheim.de/handle/123456789/24

Browse

Browsing Institut für Volkswirtschaftslehre by Sustainable Development Goals "17"

Type the first few letters and click on the Browse button
Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    A generalized representation of Faà Di Bruno'S formula using multivariate and matrix‐valued Bell polynomials
    (2025) Evers, Michael P.; Kontny, Markus
    We provide a generalization of Faà di Bruno’s formula to represent the 𝑛-th total derivative of the multivariate and vector-valued composite 𝑓 ∘𝑔. To this end, we make use of properties of the Kronecker product and the 𝑛-th derivative of the left-composite 𝑓 , which allow the use of a multivariate and matrix-valued form of partial Bell polynomials to represent the generalized Faà di Bruno’s formula. We further show that standard recurrence relations that hold for the univariate partial Bell polynomial also hold for the multivariate partial Bell polynomial under a simple transformation. We apply this generalization of Faà di Bruno’s formula to the computation of multivariate moments of the normal distribution.
  • Thumbnail Image
    Publication
    Predictor preselection for mixed‐frequency dynamic factor models: a simulation study with an empirical application to GDP nowcasting
    (2025) Franjic, Domenic; Schweikert, Karsten
    We investigate the performance of dynamic factor model nowcasting with preselected predictors in a mixed‐frequency setting. The predictors are selected via the elastic net as it is common in the targeted predictor literature. A simulation study and an application to empirical data are used to evaluate different strategies for variable selection, the influence of tuning parameters, and to determine the optimal way to handle mixed‐frequency data. We propose a novel cross‐validation approach that connects the preselection and nowcasting step. In general, we find that preselecting provides more accurate nowcasts compared with the benchmark dynamic factor model using all variables. Our newly proposed cross‐validation method outperforms the other specifications in most cases.