Abstract
Assume that the function values f(x) of an unknown regression function f: ℝ → ℝ can be observed with some random error V. To estimate the zero ϑ of f, Robbins and Monro suggested to run the recursion X n+1 = X n − a/n Y n with Y n = f(X n ) − V n . Under regularity assumptions, the normalized Robbins-Monro process, given by (X n+1 − ϑ)/√Var(X n+1, is asymptotically standard normal. In this paper Edgeworth expansions are presented which provide approximations of the distribution function up to an error of order o(1/√n) or even o(1/n). As corollaries asymptotic confidence intervals for the unknown parameter ϑ are obtained with coverage probability errors of order O(1/n). Further results concern Cornish-Fisher expansions of the quantile function, an Edgeworth correction of the distribution function and a stochastic expansion in terms of a bivariate polynomial in 1/√n and a standard normal random variable. The proofs of this paper heavily rely on recently published results on Edgeworth expansions for approximations of the Robbins-Monro process.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
O. E. Barndorff-Nielsen and D. R. Cox, Asymptotic Techniques for Use in Statistics (Chapman and Hall, London, 1989).
R. N. Bhattacharya and J. K. Ghosh, “On the Validity of the Formal Edgeworth Expansion”, Ann. Statist., 434–451 (1978).
D. R. Cox and N. Reid, “Approximations to Noncentral Distributions”, Canad. J. Statist. 15, 105–114 (1987).
J. Dippon, Asymptotische Entwicklungen des Robbins-Monro Prozesses, Habilitation Thesis (Universität Stuttgart, 1998).
J. Dippon, “Higher Order Representations of the Robbins-Monro Process”, J. Multiv. Anal. 90, 301–326 (2004).
J. Dippon, “Moments and Cumulants in Stochastic Approximation” (in press).
J. Dippon, “Edgeworth Expansions for Stochastic Approximation Theory”, Math. Methods Statist. 17, 44–65 (2008).
P. Hall, “Inverting an Edgeworth Expansion”, Ann. Statist. 11, 569–576 (1983).
P. Hall, The Bootstrap and Edgeworth Expansion (Springer, New York, 1992).
B. T. Polyak, “NewMethod of Stochastic Approximation Type”, Automat. and Remote Control 51, 937–946 (1990).
B. T. Polyak and A. B. Juditsky, “Acceleration of Stochastic Approximation by Averaging”, SIAM J. Control and Optimization 30, 838–855 (1992).
J. Renz, Konvergenzgeschwindigkeit und asymptotische Konfidenzintervalle in der stochastischen Approximation, PhD thesis (Universität Stuttgart, 1991).
H. Robbins and S. Monro, “A Stochastic Approximation Method”, Ann.Math. Statist. 22, 400–407 (1951).
D. Ruppert, “Stochastic Approximation”, in Handbook of Sequential Analysis, Ed. by G. K. Ghosh and P. K. Sen (Marcel Dekker, 1991), pp. 503–529.
J. Sacks, “Asymptotic Distribution of Stochastic Approximation Procedures”, Ann. Math. Statist. 29, 373–405 (1958).
J. H. Venter, “An Extension of the Robbins-Monro Procedure”, Ann. Math. Statist., 181–190 (1967).
H. Walk, “An Invariance Principle for the Robbins-Monro Process in a Hilbert Space”, Z. Wahrscheinlichkeitsth. verw. Gebiete 39, 135–150 (1977).
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Dippon, J. Asymptotic expansions of the Robbins-Monro process. Math. Meth. Stat. 17, 138–145 (2008). https://doi.org/10.3103/S106653070802004X
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S106653070802004X