000176829 001__ 176829
000176829 005__ 20190316235351.0
000176829 0247_ $$2doi$$a10.1080/00949655.2011.604032
000176829 022__ $$a0094-9655
000176829 02470 $$2ISI$$a000302056700008
000176829 037__ $$aCONF
000176829 245__ $$aA dimension reduction technique for estimation in linear mixed models
000176829 260__ $$bTaylor & Francis$$c2012
000176829 269__ $$a2012
000176829 336__ $$aConference Papers
000176829 520__ $$aThis paper proposes a dimension reduction technique for estimation in linear mixed models. Specifically, we show that in a linear mixed model, the maximum-likelihood (ML) problem can be rewritten as a substantially simpler optimization problem which presents at least two main advantages: the number of variables in the simplified problem is lower and the search domain of the simplified problem is a compact set. Whereas the former advantage reduces the computational burden, the latter permits the use of stochastic optimization methods well qualified for closed bounded domains. The developed dimension reduction technique makes the computation of ML estimates, for fixed effects and variance components, feasible with large computational savings. Computational experience is reported here with the results evidencing an overall good performance of the proposed technique.
000176829 6531_ $$amaximum-likelihood estimation
000176829 6531_ $$alinear mixed models
000176829 6531_ $$astochastic optimization
000176829 700__ $$0245140$$g206788$$ade Carvalho, M.
000176829 700__ $$aFonseca, M.
000176829 700__ $$aOliveira, M.
000176829 700__ $$aMexia, J. T.
000176829 7112_ $$dJul 27-31, 2010$$cTomar, PORTUGAL$$aConference of the LinStat
000176829 773__ $$j82$$tJournal Of Statistical Computation And Simulation$$q219-226
000176829 8564_ $$uhttps://infoscience.epfl.ch/record/176829/files/paper.pdf$$zn/a$$s377586$$yn/a
000176829 909C0 $$xU10124$$0252136$$pSTAT
000176829 909CO $$ooai:infoscience.tind.io:176829$$qGLOBAL_SET$$pconf$$pSB
000176829 917Z8 $$x111184
000176829 937__ $$aEPFL-CONF-176829
000176829 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000176829 980__ $$aCONF