Density Estimation for a Class of Stationary Nonlinear Processes

Author: Chanda Kamal C.  

Publisher: Springer Publishing Company

ISSN: 0020-3157

Source: Annals of the Institute of Statistical Mathematics, Vol.55, Iss.1, 2003-03, pp. : 69-82

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Let {Xt; t$${\Bbb Z}$$} be a strictly stationary nonlinear process of the form Xt = εt + Σr=1 Wrt, where Wrt can be written as a function grt−1,…, εt−r−q), {εt; t$${\Bbb Z}$$} is a sequence of independent and identically distributed (i.i.d.) random variables with E1|g < ∞ for some γ > 0 and q  0 is a fixed integer. Under certain mild regularity conditions on gr and {εt} we then show that X1 has a density function f and that the standard kernel type estimator $$\mathop f\limits^ \wedge _n (x)$$ based on a realization {X1,…, Xn} from {Xt} is, asymptotically, normal and converges a.s. to f(X) as n → ∞.