Max Westphal

  • Posted on: 24 August 2018
  • By: westphal

I am a member of the Research Training Group π3 and the Applied Statistics and Biometry working group at the University of Bremen in Germany. My research is focused on the efficient evaluation of (machine-learned) prediction models. The primary goal of my work is to enhance model evaluation and selection for medical diagnosis and prognosis. You may find some more information below and on my LinkedIn and GitHub pages.

Research Interests:

  • selection and evaluation of prediction models
  • machine learning
  • multiple testing
  • statistical simulation studies
  • medical diagnosis and prognosis

Conference Talks:

  • Westphal, Max and Werner Brannath (2018, March). Evaluation of multiple prediction models. Talk given at the annual meeting of the International Biometric Society: German Region, Frankfurt, Germany.
  • Westphal, Max and Werner Brannath (2018, July). Evaluation of multiple prediction models. Poster presentation given at the annual meeting of the International Biometric Society, Barcelona, Spain.
  • Westphal, Max and Werner Brannath (2018, July). Model selection based on the test data: how and why. Talk given at the DeepLearn 2018 summer school, Genova, Italy.
  • Westphal, Max and Werner Brannath (2019, March). A multiple testing framework for the efficient statistical evaluation of (machine-learned) prediction models. Talk given at the DAGStat 2019 conference, Munich, Germany.
  • Westphal, Max and Werner Brannath (2019, June). Improving Model Selection by Employing the Test Data. Talk and poster presentation given at the 36th International Conference on Machine Learning (ICML), Long Beach, California, USA. (https://slideslive.com/38916895/supervised-learning, ~ Min. 33)

Publications: 

  • Westphal, M. and Brannath, W. Evaluation of multiple prediction models: A novel view on model selection and performance assessment. Statistical Methods in Medical Research, forthcoming 2019.
  • Westphal, M. and Brannath, W. (2019). Improving Model Selection by Employing the Test Data. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6747–6756, Long Beach, California, USA. PMLR. (http://proceedings.mlr.press/v97/westphal19a.html)
  • Westphal, M. Simultaneous Inference for Multiple Proportions: A Multivariate Beta-Binomial Model. Manuscript submitted for publication, 2019.