2019
Том 71
№ 11

# Asymptotic normality and efficiency of a weighted correlogram

Maiboroda R. E.

Abstract

For a process X(t)=Σ j=1 M g j (t j (), where gj(t) are nonrandom given functions, $(\xi _j (t),j = \overline {1,M} )$ is a stationary vector-valued Gaussian process, Eξk(t) = 0, and Eξk(0) Eξl(τ) = r kl(τ), we construct an estimate $\hat r_{kl} (\tau ,T)$ for the functions r kl(τ) on the basis of observations X(t), t ∈ [0, T]. We establish conditions for the asymptotic normality of $\sqrt T (\hat r_{kl} (\tau ,T) - r_{kl} (\tau ))$ as T → ∞. We consider the problem of the optimal choice of parameters of the estimate $\hat r_{kl}$ depending on observations.

English version (Springer): Ukrainian Mathematical Journal 50 (1998), no. 7, pp 1067-1079.

Citation Example: Maiboroda R. E. Asymptotic normality and efficiency of a weighted correlogram // Ukr. Mat. Zh. - 1998. - 50, № 7. - pp. 937–947.

Full text