The objective of this exposition is to give an overview of the existing approaches to robust Gaussian graphical modelling. We start by thoroughly introducing Gaussian graphical models (also known as covariance selection models or concentration graph models) and then review the established, likelihood-based statistical theory (estimation, testing and model selection). Afterwards we describe robust methods and compare them to the classical approaches.
|Title of host publication||Recent Developments in Applied Probability and Statistics|
|Subtitle of host publication||Dedicated to the Memory of Jürgen Lehn|
|Editors||Luc Devroye, Bulent Karasozen, Michael Kohler, Ralf Korn|
|Number of pages||28|
|Publication status||Published - 2010|
Vogel, D., & Fried, R. (2010). On robust Gaussian graphical modelling. In L. Devroye, B. Karasozen, M. Kohler, & R. Korn (Eds.), Recent Developments in Applied Probability and Statistics: Dedicated to the Memory of Jürgen Lehn (pp. 155-182). Physica-Verlag HD. https://doi.org/10.1007/978-3-7908-2598-5_7