I am currently a post-doc at the Department of Statistics at the University of Innsbruck, from which I graduated in 2020. My PhD thesis, under the supervision of Georg J. Mayr and Achim Zeileis, was on advanced statistical methods for probabilistic forecasting within the domain of atmospheric science. The statistical models employed range from parametric to non-parametric machine learning approaches.
My research stands at the intersection between computational statistics and environmental science with a focus on probabilistic forecasting. In this framework, I am a (co-)developer of several R-packages for estimating distributional random forests and graphically evaluating probabilistic models.
R-packages
topmodels: Infrastructure for Inference and Forecasting in Probabilistic Models
- Unified infrastructure for probabilistic models and distributional regressions: Computation of probabilities, densities, scores, and Hessians.
- Probabilistic forecasting.
- Diagnostic graphics such as rootograms, PIT histograms, reliagrams (reliability diagrams), (randomized) quantile residual Q-Q plots, and worm plots.
- Modular object-oriented implementation with support for many model objects, including lm, glm, crch, disttree, and more to come.
disttree: Trees and Forests for Distributional Regression
- Infrastructure for fitting distributional regression trees and forests based on maximum-likelihood estimation of parameters for specified distribution families, for example from the GAMLSS family.
circtree: Regression Trees and Forests for Circular Responses
- Infrastructure for fitting distributional trees and forests based on maximum-likelihood estimation of parameters for a circular response, as well as regression methods for a circular response based on maximum-likelihood estimation are provided.
- For both approaches the von Mises distribution is employed as circular response distribution.
