TU Wien CAIML

Overview News Researchers & Projects Team Partners

Patricia Puchhammer

patricia-puchhammer.png

On This Page

Short Bio

Patricia Puchhammer is a PhD student in the Computational Statistics (CSTAT) research group, part of the Institute of Statistics and Mathematical Methods in Economics. She is involved in the EU-Horizon project SEMACRET - Sustainable Exploration of Critical Raw Materials, which aims to ensure the supply of materials essential for Europe’s green transition. Her research within SEMACRET focuses on developing robust methods for analyzing data as well as spatial data within a multi-group framework.

Patricia earned her BSc in 2018 and Dipl. Ing. degree in 2022 from TU Wien, specializing in macroeconomic modeling, including monetary policies, which was the focus of her master’s thesis. She also gained expertise in statistical methods. During her studies, she took on teaching responsibilities as a tutor. Before joining CSTAT, Patricia worked as a data scientist at the Ludwig Boltzmann Institute for Lung Health, where she deepened her knowledge in medical statistics.

PhD Project - Robust Statistics for Multi-group Data

Supervised by Peter Filzmoser

Patricia’s PhD research centers on developing outlier-robust methods for spatial and multi-group data. Her goal is to create parameter estimation techniques that provide group-specific estimates while leveraging contextual information from other groups. Her recent work includes a focus on cellwise outlyingness and an innovative approach to mixture models for grouped data. Within the SEMACRET project, these novel methodologies, combined with Compositional Data Analysis, offer new ways to detect spatial outliers, that can help identify potential new mineral deposits.

Publications and Conferences

Papers

  • Puchhammer, P., Wilms, I., and Filzmoser, P. (2025). A smooth multi-group Gaussian Mixture Model for cellwise robust covariance estimation. arXiv preprint arXiv:2504.02547.
  • Puchhammer, P., Wilms, I., and Filzmoser, P. (2024). Sparse outlier-robust PCA for multi-source data. arXiv preprint arXiv:2407.16299.
  • Puchhammer, P., Kalubowila, C., Braus, L., Pospiech, S., Sarala, P., and Filzmoser, P. (2024). A performance study of local outlier detection methods for mineral exploration with geochemical compositional data. Journal of Geochemical Exploration, 258, 107392. DOI: 10.1016/j.gexplo.2024.107392.
  • Puchhammer, P., and Filzmoser, P. (2024). Spatially smoothed robust covariance estimation for local outlier detection. Journal of Computational and Graphical Statistics, 33(3), 928-940. DOI: 10.1080/10618600.2023.2277875.
  • Ofenheimer, A., Breyer, M. K., Wouters, E. F., Schiffers, C., Hartl, S., Burghuber, O. C., Krach, F., Maninno, D., Franssen, F., Mraz, T., Puchhammer, P., and Breyer-Kohansal, R. (2024). The effect of body compartments on lung function in childhood and adolescence. Clinical Nutrition, 43(2), 476-481.
  • Danninger, K., Burghuber, O., Breyer, M. K., Puchhammer, P., Ofenheimer, A., Breyer-Kohansal, R., Kaufmann, C., Hartl,S., and Weber, T. (2023). Prevalence and determinants of vascular aging: the LEAD study. Artery Research, 29(1).
  • Schiffers, C., Faner, R., Ofenheimer, A., Sunanta, O., Puchhammer, P., Mraz, T., Breyer, M.K., Burghuber, O.C., Hartl, S., Agusti, A. and Breyer-Kohansal, R. (2023). Supranormal lung function: prevalence, associated factors and clinical manifestations across the lifespan. Respirology, 28(10), 942-953.
  • Puchhammer, P. (2021). The effects of quantitative easing in a new Keynesian small open economy model. Master’s thesis, Technische Universität Wien. Schnabl, A., Lappöhn, S., Plank, K., and Puchhammer, P. (2019). Umwegrentabilität des österreichischen EU-Ratsvorsitzes 2018.
  • Schnabl, A., Lappöhn, S., Plank, K., and Puchhammer, P.. (2019). Ökonomische Effekte der Wien Holding für Österreich und seine Bundesländer.

Presentations

  • Puchhammer, P., Wilms, I., and Filzmoser, P. (2024). Robust sparse PCA for spatial data. ICORS meets DSSV 2024, Fairfax, United States of America.
  • Puchhammer, P., Filzmoser, P., and Wilms, I. (2024). Groupwise sparse PCA for spatial data. Austrian Statistical Days 2024, Vienna, Austria.
  • Puchhammer, P., and Filzmoser, P. (2023). Spatial outlier detection using the spatially smoothed MRCD. 22nd Annual Conference of the International Association for Mathematical Geosciences 2023 (IAMG2023), Trondheim, Norway.
  • Puchhammer, P., and Filzmoser, P. (2023). Detecting Local Outliers Using the Spatially Smoothed MRCD Estimator. Olomoucian Days of Applied Mathematics (ODAM 2023), Olomouc, Czech Republic.
  • Puchhammer, P., and Filzmoser, P. (2023). A spatially smoothed MRCD estimator for local outlier detection. International Conference on Robust Statistics (ICORS 2023), Toulouse, France.