Clusters, outliers, and regression: fixed point clusters
نویسندگان
چکیده
منابع مشابه
Regression Fixed Point Clusters: Motivation, Consistency and Simulations
In this paper, the theoretical foundation of Least Squares-Fixed Point Clusters for clusterwise linear regression is given in full detail, as well as a discussion of the computation and application of the approach and a comparison with other cluster analysis methods based on stochastic models. Fixed Point Clustering is based on iteratively reweighted estimation with zero weight for all outliers...
متن کاملCOMPUTATIONAL ENUMERATION OF POINT DEFECT CLUSTERS IN DOUBLE- LATTICE CRYSTALS
The cluster representation matrices have already been successfully used to enumerate close-packed vacancy clusters in all single-lattice crystals [I, 2]. Point defect clusters in double-lattice crystals may have identical geometry but are distinct due to unique atomic postions enclosing them. The method of representation matrices is extended to make it applicable to represent and enumerate ...
متن کاملDissolution and isolation robustness of fixed point clusters
The concepts of a dissolution point (which is an adaptation of the breakdown point concept to cluster analysis) and isolation robustness are introduced for general clustering methods, generating possibly overlapping clusterings. Robustness theorems for fixed point clusters (Hennig (2002, 2003, 2005)) are shown.
متن کاملQTAIM study of Bonding and Structure of Pure Atomic Clusters,Part III : Nn Clusters (n= 4,6)
DFT and QTAIM computations have been performed on numbers of pure nitrogen cluster speciesi.e. Nn (n = 4, 6) for investigating the structure and bonding. This study is critical since thesemolecules have been nominated as the good synthetic targets of High Energy Materials (HEM).0nthe other hand the decomposition mechanism is closely depends on the bonding pattern. Thislatter concept was searche...
متن کاملClustered regression with unknown clusters
We consider a collection of prediction experiments, which are clustered in the sense that groups of experiments exhibit similar relationship between the predictor and response variables. The experiment clusters as well as the regression relationships are unknown. The regression relationships define the experiment clusters, and in general, the predictor and response variables may not exhibit any...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Multivariate Analysis
سال: 2003
ISSN: 0047-259X
DOI: 10.1016/s0047-259x(02)00020-9