English

Efficiency of Z-estimators indexed by the objective functions

Statistics Theory 2015-09-16 v1 Methodology Statistics Theory

Abstract

We study the convergence of ZZ-estimators θ^(η)Rp\widehat \theta(\eta)\in \mathbb R^p for which the objective function depends on a parameter η\eta that belongs to a Banach space H\mathcal H. Our results include the uniform consistency over H\mathcal H and the weak convergence in the space of bounded Rp\mathbb R^p-valued functions defined on H\mathcal H. Furthermore when η\eta is a tuning parameter optimally selected at η0\eta_0, we provide conditions under which an estimated η^\widehat \eta can be replaced by η0\eta_0 without affecting the asymptotic variance. Interestingly, these conditions are free from any rate of convergence of η^\widehat \eta to η0\eta_0 but they require the space described by η^\widehat \eta to be not too large. We highlight several applications of our results and we study in detail the case where η\eta is the weight function in weighted regression.

Cite

@article{arxiv.1509.04413,
  title  = {Efficiency of Z-estimators indexed by the objective functions},
  author = {François Portier},
  journal= {arXiv preprint arXiv:1509.04413},
  year   = {2015}
}

Comments

25 pages, 4 figures

R2 v1 2026-06-22T10:56:51.872Z