Cantoni, Eva Mills Flemming, Joanna Ronchetti, Elvezio 2009 We adapt Breiman’s (1995) nonnegative garrote method to perform variable selection in nonparametric additive models. The technique avoids methods of testing for which no general reliable distributional theory is available. In addition it removes the need for a full search of all possible models, something which is computationally intensive, especially when the number of variables is moderate to high. The method has the advantages of being conceptually simple and computationally fast. It provides accurate predictions and is effective at identifying the variables generating the model. To illustrate our procedure, we analyze logbook data on blue sharks (Prionace glauca) from the United States pelagic longline fishery. In addition we compare our proposal to a series of available alternatives by simulation. The results show that in all cases our methods perform better or as these alternatives. application/pdf https://localhost:5000/ark:/12658/srd1318250 https://susi.usi.ch/global/documents/318250 https://susi.usi.ch/documents/318250/files/ronchetti_SM_2011.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.1177/1471082X1001100304 info:eu-repo/semantics/altIdentifier/ark/12658/srd1318250 info:eu-repo/semantics/openAccess License undefined Statistical modelling. - Sage publications. - 2011, vol. 11, no. 3, p. 237-252 Blue shark logbook data cross-validation nonnegative garrote nonparametric regression shrinkage methods variable selection info:eu-repo/classification/udc/33 Variable selection in additive models by nonnegative garrote http://purl.org/coar/resource_type/c_6501