Abstract
A transformation of a discrete-time martingale with conditionally Gaussian increments into a sequence of i.i.d. standard Gaussian random variables is proposed as based on a sequence of stopping times constructed using the quadratic variation. It is shown that sequential estimators for the parameters in AR(1) and generalized first-order autoregressive models have a nonasymptotic normal distribution.
Similar content being viewed by others
References
A. A. Novikov, Teor. Veroyatn. Ee Primen. 16 (2), 394–396 (1971).
R. S. Liptser and A. N. Shiryaev, Statistics of Random Processes (Nauka, Moscow, 1974; Springer-Verlag, Berlin, 1977/1978).
A. N. Shiryaev and V. G. Spokoiny, Statistical Experiments and Decision: Asymptotic Theory (World Scientific, Singapore, 2000).
A. N. Shiryaev, Probability (Nauka, Moscow, 1984; Springer-Verlag, Berlin, 1994).
P. W. Mikulski and M. J. Monsour, J. Time Ser. Anal. 12 (3), 235–253 (1991).
T. L. Lai and D. Siegmund, Ann. Stat. 11, 478–485 (1983).
P. E. Greenwood and A. N. Shiryaev, Stoch. Stoch. Rep. 38, 49–56 (1992).
V. Z. Borisov and V. V. Konev, Autom. Remote Control 38 (10), 1475–1480 (1977).
S. M. Pergamenshchikov, Theory Probab. Appl. 36 (1), 36–49 (1991).
T. W. Anderson, Proc. Am. Math. Soc. 8 (2), 170–176 (1955).
S. M. Pergamentschikov and A. N. Shiryaev, Ann. Acad. Sci. Fenn. Ser. A.I. Math. 17, 111–116 (1992).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © V.V. Konev, 2016, published in Doklady Akademii Nauk, 2016, Vol. 471, No. 5, pp. 523–527.
Rights and permissions
About this article
Cite this article
Konev, V.V. On one property of martingales with conditionally Gaussian increments and its application in the theory of nonasymptotic inference. Dokl. Math. 94, 676–680 (2016). https://doi.org/10.1134/S1064562416060235
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064562416060235