Plausibility of Databases and the Relation to Imputation Methods - Softcover

Revision with unchanged content. The estimation of the plausibility of a set of observations basically depends on the main structure which stands behind these data. Observations which fit into this estimated structure seem more plausible, than observations with large distance to such structure estimates. For representing the structure of a data set, here principal components are used. Since single observations which do not follow the main structure of a data set (outliers) should not influence such estimations, robust methods are considered primarily in this context. The estimation of missing values is based on principal component analysis as well. Iteratively principal components are estimated, and observations are projected onto them until convergence of this process. In this context existing algorithms have been improved concerning the quality of imputation and runtime behavior. In particular this improvement focuses on the projection methods which are used to project observations containing missings onto principal components.

Heinrich Fritz: 2003-2007 Computer science studies at the Vienna University of Technology.Graduated 2006 in Data Engineeringand Statistics, 2007 in Business Engineering and Computer Science as well as Computer Science Management.Peter Filzmoser: studied Applied Mathematics at the ViennaUniversity of Technology, where he also wrote hisdoctoral thesis and habilitation. His research is in the field ofmultivariate and robust statistics.

(born 1968) studied Applied Mathematics at the ViennaUniversity of Technology, Austria, where he also wrote hisdoctoral thesis and habilitation. His research is in the field ofmultivariate and robust statistics. Since 2001 he is dozent atthe Statistics Department at Vienna University of Technology.