单调缺失机制下高维纵向线性回归模型的变量选择

在响应变量带有单调缺失的情形下考虑高维纵向线性回归模型的变量选择.主要基于逆概率加权广义估计方程提出了一种自动的变量选择方法,该方法不使用现有的惩罚函数,不涉及惩罚函数非凸最优化的问题,并且可以自动地剔除零回归系数,同时得到非零回归系数的估计.在一定正则条件下,证明了该变量选择方法具有Oracle性质.最后,通过模拟研究验证了所提出方法的有限样本性质.

Variable selection for high-dimensional longitudinal linear regression models with monotone missing patterns

This paper considers the problem of variable selection in high-dimensional longitudi-nal linear regression models with monotone missing patterns. A new variable selection procedure is proposed based on the smooth-threshold inverse probability weighted generalized estimating equation. The proposed procedure avoids the convex optimization problem without using penalty functions. Be-sides, the proposed method can automatically eliminate inactive predictors by setting the corresponding parameters to be zero, and simultaneously estimate the nonzero regression coefficients. Under some regularity conditions, the variable selection procedure is proved to have Oracle property. Finally, some simulation studies are conducted to examine the finite sample property of the proposed variable selec-tion procedure.