Lô, Serigne N. Ronchetti, Elvezio 2009 In the framework of generalized linear models, the nonrobustness of classical estimators and tests for the parameters is a well known problem and alternative methods have been proposed in the literature. These methods are robust and can cope with deviations from the assumed distribution. However, they are based on ¯rst order asymptotic theory and their accuracy in moderate to small samples is still an open question. In this paper we propose a test statistic which combines robustness and good accuracy for moderate to small sample sizes. We combine results from Cantoni and Ronchetti (2001) and Robinson, Ronchetti and Young (2003) to obtain a robust test statistic for hypothesis testing and variable selection which is asymptotically Â2¡distributed as the three classical tests but with a relative error of order O(n¡1). This leads to reliable inference in the presence of small deviations from the assumed model distribution and to accurate testing and variable selection even in moderate to small samples. application/pdf https://susi.usi.ch/global/documents/318256 https://n2t.net/ark:/12658/srd1318256 https://susi.usi.ch/documents/318256/files/ronchetti_JMA_2009_1.pdf https://susi.usi.ch/documents/318256/files/ronchetti_JMA_2009_2.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.1016/j.jmva.2009.06.012 info:eu-repo/semantics/altIdentifier/ark/12658/srd1318256 info:eu-repo/semantics/openAccess License undefined Journal of multivariate analysis. - Academic Press. - 2009, vol. 100, no. 9, p. 2126-2136 M-estimators Monte Carlo Robust inference Robust variable selection Saddlepoint techniques Saddlepoint Test info:eu-repo/classification/udc/33 Robust and accurate inference for generalized linear models http://purl.org/coar/resource_type/c_6501