Honest Confidence Sets for Sparsely and Non-Sparsely Tuned Model Selection Estimators

• Antragstellerin: Professorin Dr. Ulrike Schneider
• Fachliche Zuordnung: Mathematik
• Förderung: Förderung von 2011 bis 2017
• Projektkennung: Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 40095828

In this project we want to investigate the distributional properties of shrinkage estimators, such as the popular Lasso estimator and other regularization methods, with the aim of deriving honest confidence sets based on the these estimators. This kind of estimators has seen immense interest in recent statistics literature. However, it is still largely unknown how to construct valid confidence sets based on such an estimator – a question that is both of theoretical as well as of practical interest.

• DFG-Verfahren: Forschungsgruppen
• Teilprojekt zu: FOR 916: Swiss-German Bilateral Research Unit on: Statistical Regularisation and Qualitative Constraints - Inference, Algorithms, Asymptotics and Applications
• Internationaler Bezug: Österreich