Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/23265

Title: Finite Information Limit Variance-covariance Structures: Is the Entire Dataset Needed for Analysis?
Authors: Nassiri, Vahid
Molenberghs, Geert
Verbeke, Geert
Issue Date: 2016
Publisher: IEEE
Citation: Smari, W.W. (Ed.). 2016 International Conference on High Performance Computing & Simulation (HPCS), IEEE,p. 736-742
Abstract: Finite Information Limit (FIL) variance-covariance structures for hierarchical data are introduced and examined: for such data, it is often possible to analyze only a sometimes very small subset, leading to considerable computation time gain, with almost no efficiency loss. A central example is compound-symmetry. A simple approach is proposed to detect this property in a given dataset.
Notes: [Nassiri, Vahid; Verbeke, Geert] Katholieke Univ Leuven, I BioStat, B-3000 Louvain, Belgium. [Molenberghs, Geert] Univ Hasselt, I BioStat, Hasselt, Belgium. [Molenberghs, Geert] Katholieke Univ Leuven, Leuven, Belgium. [Verbeke, Geert] Univ Hasselt, Hasselt, Belgium.
URI: http://hdl.handle.net/1942/23265
DOI: 10.1109/HPCSim.2016.7568408
ISI #: 000389590600100
ISBN: 9781509020881
Category: C1
Type: Proceedings Paper
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version459.95 kBAdobe PDF
Peer-reviewed author version468.52 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.