Project Details
Projekt
FOR 5381: Mathematical Statistics in the Information Age - Statistical Efficiency and Computational Tractability
Subject Area
Mathematics
Term
since 2021
Website
Homepage
Project identifier
Deutsche Forschungsgemeinschaft (DFG) - Project number 460867398
In the information age, the importance of data together with reliable and meaningful statistical evaluation is greater than ever. In face of massive amounts of data, however, new challenges enter statistical methodology. Storage or privacy constraints require even clean raw data to be preprocessed, and its massiveness typically leads to computational intractability of subsequently applied classical efficient statistical methodology. Usually, preprocessed data do not share the distributional properties of the raw data any longer. Moreover, statistically efficient data preprocessing typically depends on the given task of subsequent statistical inference. Hence, both processing steps are inseparably linked. New concepts have to be developed which guarantee validity and efficiency on potentially preprocessed data sets while being computationally tractable at the same time for massive data. Our aim is to provide exactly this conjoint development, therefore influencing all scientific branches of modern statistical data analysis. Within the funding period, this research unit shall successfully develop comprehensive statistical methodology which addresses these new challenges of modern data analysis.
DFG Programme
Research Units
International Connection
Austria
Projects
- Classification -- Preprocessed and high-dimensional data sets (Applicant Rohde, Angelika )
- Computationally tractable bootstrap for high-dimensional data (Applicants Dette, Holger ; Rohde, Angelika )
- Coordination Funds (Applicant Rohde, Angelika )
- Optimal actions and stopping in sequential learning (Applicants Carpentier, Alexandra ; Reiß, Markus )
- Sublinear time methods with statistical guarantees (Applicants Dette, Holger ; Munk, Axel )
- Supersmooth functional data analysis and PCA-preprocessing (Applicant Meister, Alexander )
Spokesperson
Professorin Dr. Angelika Rohde
