Feature significance in generalized additive models

UTSePress Research/Manakin Repository

Search UTSePress Research

Advanced Search


My Account

Show simple item record

dc.contributor.author Ganguli, Bhaswati en_US
dc.contributor.author Wand, Matt en_US
dc.contributor.editor en_US
dc.date.accessioned 2011-02-07T06:17:55Z
dc.date.available 2011-02-07T06:17:55Z
dc.date.issued 2007 en_US
dc.identifier 2010000265 en_US
dc.identifier.citation Ganguli Bhaswati and Wand Matt 2007, 'Feature significance in generalized additive models', Springer New York LLC, vol. 17, pp. 179-192. en_US
dc.identifier.issn 0960-3174 en_US
dc.identifier.other C1UNSUBMIT en_US
dc.identifier.uri http://hdl.handle.net/10453/13000
dc.description.abstract This paper develops inference for the significance of features such as peaks and valleys observed in additive modeling through an extension of the SiZer-type methodology of Chaudhuri and Marron (1999) and Godtliebsen et al. (2002, 2004) to the case where the outcome is discrete. We consider the problem of determining the significance of features such as peaks or valleys in observed covariate effects both for the case of additive modeling where the main predictor of interest is univariate as well as the problem of studying the significance of features such as peaks, inclines, ridges and valleys when the main predictor of interest is geographical location. We work with low rank radial spline smoothers to allow to the handling of sparse designs and large sample sizes. Reducing the problem to a Generalised Linear Mixed Model (GLMM) framework enables derivation of simulation-based critical value approximations and guards against the problem of multiple inferences over a range of predictor values. Such a reduction also allows for easy adjustment for confounders including those which have an unknown or complex effect on the outcome. A simulation study indicates that our method has satisfactory power. Finally, we illustrate our methodology on several data sets. en_US
dc.language en_US
dc.publisher Springer New York LLC en_US
dc.relation.isbasedon http://dx.doi.org/10.1007/s11222-006-9011-x en_US
dc.title Feature significance in generalized additive models en_US
dc.parent Statistics and Computing en_US
dc.journal.volume 17 en_US
dc.journal.number en_US
dc.journal.number 2 en_US
dc.publocation United States en_US
dc.identifier.startpage 179 en_US
dc.identifier.endpage 192 en_US
dc.cauo.name SCI.Mathematical Sciences en_US
dc.conference Verified OK en_US
dc.for 010400 en_US
dc.personcode 0000064878 en_US
dc.personcode 110509 en_US
dc.percentage 100 en_US
dc.classification.name Statistics en_US
dc.classification.type FOR-08 en_US
dc.edition en_US
dc.custom en_US
dc.date.activity en_US
dc.location.activity en_US
dc.description.keywords Additive models - Best linear unbiased prediction (BLUP) - Bivariate smoothing - Generalised linear mixed models - Geostatistics - Low-rank mixed models - Penalised splines - Penalised quasi-likelihood (PQL) en_US
dc.staffid 110509 en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record