{"64790":{"#nid":"64790","#data":{"type":"event","title":"Variable Selection in Linear Mixed Effects Models","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETITLE:\u003C\/strong\u003E Variable Selection in Linear Mixed Effects Models\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ESPEAKER:\u003C\/strong\u003E Professor Yingying Fan\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EABSTRACT:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThis\n paper is concerned with the selection and estimation of fixed and \nrandom effects in linear mixed effects models. We propose a class of \nnonconcave penalized profile likelihood methods for selecting and \nestimating significant fixed effects parameters simultaneously for the \nsetting in which the number of predictors is allowed to grow \nexponentially with sample size.\u003Cbr \/\u003E\nTo study the sampling properties of the proposed procedure, we establish\n a new theoretical framework which is distinguished from the existing \nones (Fan and Li, 2001). We show that the proposed procedure enjoys the \nmodel selection consistency. We further propose a group variable \nselection strategy to simultaneously select and estimate the significant\n random effects. The resulting random effects estimator is compared with\n the oracle-assisted Bayes estimator. We prove that, with probability \ntending to one,\u0026nbsp; the proposed procedure identifies all true random \neffects, and furthermore, that the resulting estimates are close to the \noracle-assisted Bayes estimates for the selected random effects. In the \nrandom effects selection and estimation, the dimensionality is also \nallowed to increase exponentially with sample size. Monte Carlo \nsimulation studies are conducted to examine the finite sample \nperformances of the proposed procedures. We further illustrate the \nproposed procedures via a real data example.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Variable Selection in Linear Mixed Effects Models"}],"uid":"27187","created_gmt":"2011-03-07 12:40:53","changed_gmt":"2016-10-08 01:54:26","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2011-03-17T13:00:00-04:00","event_time_end":"2011-03-17T14:00:00-04:00","event_time_end_last":"2011-03-17T14:00:00-04:00","gmt_time_start":"2011-03-17 17:00:00","gmt_time_end":"2011-03-17 18:00:00","gmt_time_end_last":"2011-03-17 18:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}