RT Journal Article
T1 Testing in generalized partially linear models: A robust approach
A1 Boente Boente, Graciela
A1 Cao Abad, Ricardo José
A1 González Manteiga, Wenceslao
A1 Rodríguez, Daniela
K1 Generalized partially linear models
K1 Kernel weights
K1 Rate of convergence
K1 Robust testing
AB In this paper, we introduce a family of robust statistics which allow to decide betweena parametric model and a semiparametric one. More precisely, under a generalizedpartially linear model, i.e., when the observations satisfy yi|(xi, ti) ∼ F (·, µi) with µi =Hη(ti) + xti βand H a known link function, we want to test H0 : η(t) = α + γ t againstH1 : η is a nonlinear smooth function. A general approach which includes robust estimatorsbased on a robustified deviance or a robustified quasi-likelihood is considered. Theasymptotic behavior of the test statistic under the null hypothesis is obtained
PB Elsevier
SN 0167-7152
YR 2013
FD 2013
LK http://hdl.handle.net/10347/18530
UL http://hdl.handle.net/10347/18530
LA eng
NO Boente, G., Cao, R., González Manteiga, W., & Rodriguez, D. (2013). Testing in generalized partially linear models: A robust approach. Statistics & Probability Letters, 83(1), 203-212. doi: 10.1016/j.spl.2012.08.031
NO This research was partially supported by Grants 20020100100276 and 20020100300057 from the Universidad de BuenosAires, pip 112-200801-00216 from conicet, pict 0821 from anpcyt at Argentina and also by Spanish Grant MTM2008-03010/MTM of the Ministerio Español de Ciencia e Innovación and XUNTA Grant 10MDS207015PR
DS Minerva
RD 24 abr 2026