REACT Fits to Linear Models and Scatterplots

Gespeichert in:
Bibliographische Detailangaben
Titel: REACT Fits to Linear Models and Scatterplots
Autoren: Rudolf Beran
Weitere Verfasser: The Pennsylvania State University CiteSeerX Archives
Quelle: ftp://statlab.uni-heidelberg.de/pub/reports/by.series/beitrag.49.ps
Publikationsjahr: 1998
Bestand: CiteSeerX
Schlagwörter: risk estimation, adaptation, discrete cosine transform, economical basis, minimum CL, symmetric linear smoother, asymptotic minimax, shrinkage
Beschreibung: this paper, that yields superefficient fits to the Gaussian linear model. The risk of REACT fits under quadratic loss is often far smaller than the risk of the classically efficient least squares fit. Applied to the one-way layout, REACT fits generate automatic scatterplot smoothers that compete well
Publikationsart: text
Dateibeschreibung: application/postscript
Sprache: English
Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.3450
Verfügbarkeit: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.3450
Rights: Metadata may be used without restrictions as long as the oai identifier remains attached to it.
Dokumentencode: edsbas.9504555C
Datenbank: BASE
Beschreibung
Abstract:this paper, that yields superefficient fits to the Gaussian linear model. The risk of REACT fits under quadratic loss is often far smaller than the risk of the classically efficient least squares fit. Applied to the one-way layout, REACT fits generate automatic scatterplot smoothers that compete well