Single-index coefficient models for nonlinear time
ries
好词摘抄200个期刊名称： Journal of Nonparametric Statistics
作者： Tracy Z. Wu,Haiqun Lin,Yan Yu
作者机构： JPMorgan Cha Bank,Biostatistics, Business Analytics
年份： 2011年
斗鸡眼
刎颈之交是什么意思期号： 第1-2期
关键词： dimension reduction; forecasting; multivariate; PS; smoothing
parameter; varying- coefficient model
好奇心害死猫摘要：The single-index coefficient model, where the coefficients are functions of an index of a covariat家喻户晓
e vector, is a powerful tool for modelling nonlinearity in multivariate estimation. By reducing the covariate vector to an index which is usually a linear combination of covariates, the single-index coefficient model overcomes the well-known phenomenon of 'cur-of-dimensionality'. We estimate the univariate varying coefficients with penalid splines (PS). An iterative data-driven algorithm is developed, adaptively lecting the index. The algorithm is bad on the obrvation that given an estimated index, the varying-coefficient model using PS is esntially a linear ridge regression with spline bas. Our experiments show that the propod algorithm gives rapid convergence. We also establish large sample properties assuming
邀请函二本补录内容由中国教育图书进出口有限公司引进
蛋清的作用
