Abstract
Let x1,..., xn be a repeated sample from a one-dimensional population with distribution function (d.f.) F(x−η, θ), depending on a structure parameter θ∈Θ⊂R 1 and a nuisance shift parameter η∈ R1. The estimator which eliminates ν In a natural manner, has the form\(\sum\limits_1^n {\psi (x_i - \overline x ,\theta ) = 0,\overline x = (x_1 + ... + x_n )/n}\) and the simplest among them, corresponding to a functionψ (u, θ), quadratic in u, leads to the estimate θ (m2), where\(m_2 = \sum\limits_1^n {(x_i - \overline x )^2 /n}\) which has to be considered as an estimate of θ by the method of moments with the elimination of the nuisance parameter n. If for some integer k ≥ 1, 1°) the d.f. F(x, θ) has a finite moment of order 2k, 2°) its central moments μ2(θ), ..., μk(θ) are three times and μk+1(9).... μ2k(θ) are twice continuously differentiable in the domain Θ and μ2′(θ) ≠ 0, 3° as n → ∞, the limit covariance matrix of the centralized and normalized vector √n ∥ m2-μ2(θ) ...,mR-μR(θ)∥ of the central sample moments mj is nonsingular, θ∈Θ, then the estimate θ(m2) is asymptotically admissible (and optimal) in the class of estimates defined by the estimators λo(θ) + λ2(θ)m2 + ... + λk(θ)mk=0 if and only if the moments μ5(θ),..., μk+2 (θ) are determined in terms of μ2(θ), μ3(θ), μ4(θ) in the following recurrent manner;
The asymptotic admissibility is understood in the same generally accepted sense as in [1], where a similar result has been obtained for families of d.f. containing only a structure parameter.
Similar content being viewed by others
Literature cited
A. M. Kagan, “A graded scale of parametric families of distributions and estimates of the parameter, based on the sample mean,” in: Problemy Ustoichivosti Stokhasticheskikh Modelei. Tr. Sem., VNIISI, Moscow (1981), pp. 41–47.
C. R. Rao, Linear Statistical Inference and Its Applications, Wiley, New York (1965).
A. M. Kagan, “The admissibility of estimates, obtained by the method of moments within certain classes of estimates,” Teor. Veroyatn. Primen.,26, No. 4, 875–876 (1981).
V. P. Godambe, “An optimum property of regular maximum likelihood estimation,” Ann. Math. Stat.,31, No. 4, 1208–1211 (1960).
H. Cramer, Mathematical Methods of Statistics, Princeton Univ. Press, Princeton (1946).
Additional information
Translated from Problemy Ustoichivosti Stokhasticheskikh Modelei — Trudy Seminara, pp. 61–66, 1982.
Rights and permissions
About this article
Cite this article
Kagan, A.M. Admissibility of an estimate obtained by the method of moments in the presence of a nuisance shift parameter. J Math Sci 35, 2499–2504 (1986). https://doi.org/10.1007/BF01121462
Issue Date:
DOI: https://doi.org/10.1007/BF01121462