Sie sind hier:


Prof. Arne Bathke (University of Salzburg)

Photo Credit: Gruber/Haigermoser, Uni Salzburg




Research Associates:

Joined D-A-CH-Lead Agency Project with Arne Bathke, University of Salzburg: "Inference methods for multivariate and high-dimensional data"

Funded by:

German Research Foundation (D-A-CH-Lead-Agency Project with Arne Bathke, University of Salzburg).

Projectnumber: PA 2409/4-1,  Duration: 2016-2019 .

Project Objectives:

Together with our collaboration partners from Salzburg, it was the aim of this project to develop inference
methods for multivariate and high-dimensional data. Thereby a major focus laid on global inferential methods
such as tests and confidence regions. We thereby wanted to focus on two types of models:
(A) Semiparametric models with null hypothesis (or confidence regions) formulated in terms of means or
covariances and
(B) purely nonparametric methods which led to rank-based procedures that are invariant under monotone
transformations of the individual responses and remain valid in case of ordinal categorical data, or in
situations where some of the response variables are quantitative, others ordinal.

Beyond that, we wanted to give special attention to the performance of the methods for small samples, high dimension or large number of groups and combinations thereof. Thereto we wanted to investigate the application of either moment-based approximations or resampling methods.



  • Sattler, P and Pauly, M (2018). Inference For High-Dimensional Split-Plot-Designs: A Unified Approach for Small to Large Numbers of Factor Levels. Electronic Journal of Statistics  12, 2743--2805.
  • Dobler, D and Pauly, M (2018). Bootstrap- and permutation-based Inference for the Mann-Whitney Effect for Right-Censored and Tied Data. TEST 27, 639--658.
  • Dobler, D, Friedrich, S and Pauly, M (2019). Nonparametric MANOVA in meaningful effects. Annals of the Institute of Statistical Mathematics, to appear (
  • Zimmermann, G, Pauly, M and Bathke, A.C. (2019a). Small-sample performance and underlying assumptions of a bootstrap-based inference method for a general analysis of covariance model with possibly heteroskedastic and nonnormal errors. Statistical Methods in Medical Research 28, 3808--3821.
  • Zimmermann, G, Pauly, M and Bathke, A.C. (2019b). Multivariate analysis of covariance when standard assumptions are violated. preprint arXiv:1902.10195
  • Ramosaj, Burim, Amro, Lubna, & Pauly, Markus. 2019. A cautionary tale on using imputation methods for inference in matched pairs design. preprint arXiv:1806.06551


  • Brunner, E., Konietschke, F., Bathke, A. C., and Pauly, M. (2019). Ranks and Pseudo-Ranks-Paradoxical Results of Certain Rank Tests. arXiv preprint arXiv:1802.05650. .
  • Sattler, P., Bathke, A. C. and Pauly, M. Testing Hypotheses about Covariance Matrices in General MANOVA Designs.  arXiv preprint arXiv:1909.06205.
  • Sattler, P. {Manifold Asymptotics of Quadratic-Form-Based
    Inference in Repeated Measures Designs. {arXiv preprint arXiv:1911.01979v1}}.





  • Joachim Hartung Prize for Paavo Sattler received for his talk upon: "Inference for high-Dimensional split-plot-designs: A unified approach for small to large numbers of factor levels", see Sattler and Pauly (2018)
  • Leopold-Karl-Schmetterer-Prizefor Georg Zimmermann received for his talk upon: "Comparing multivariate outcomes between groups while adjusting for baseline measurements", see the preprint Zimmermann et al. (2019)
  • Young Investigator Award 2018 (First prize in the category "Natural and Life Sciences" at the University of Salzburg) for his abstract and talk about the paper Zimmermann et al. (2019)