Speciality:
01.01.05 (Probability theory and mathematical statistics)
Birth date:
10.01.1947
Website: https://www.math.spbu.ru/user/nikitin Keywords: nonparametric statistics; hypothesis testing;large deviations; small deviations; asymptotic efficiency of tests; U- and V-statistics; rank statistics; arc-sine law;characterization of distributions.
Subject:
The problem of large deviation probabilities for a large class of functionals of empirical measures was solved. This enabled to calculate for the first time the Bahadur, Chernoff and Hodges–Lehmann efficiencies of numerous nonparametric statistics for goodness-of-fit, homogeneity, symmetry and independence testing. The notion of local optimality domain was introduced and investigated for many nonparametric statistics. Some original characterization theorems connected with the property of local optimality were found. In a series of joint works with E.V.Ponikarov we studied the large deviation asymptotics of Chernoff type for U- and V-statistics with general kernels. Some generalizations of arc-sine law were obtained jointly with E. Orsingher. Jointly with N. Henze we introduced and studied new goodness-of-fit tests based on the integrated empirical process.
Main publications:
Nikitin Yakov, Asymptotic efficiency of nonparametric tests. Cambridge University Press, 1995.
Nikitin Ya. Yu., Conti P. L. Asymptotic efficiency of independence tests based on Gini's rank association coefficient, Spearman's footrule and their generalizations // Commun. in Statist. Theory and Methods, 1999, v. 28, no. 2, p. 453–465.
Nikitin Ya. Yu., Henze N. A new approach to goodness-of-fit testing based on the integrated empirical process // J. Nonpar. Statist. 12, 2000, 391–416.
Nikitin Ya. Yu., Orsingher E. Conditional sojourn distributions of "processes" related to the third-order and fourth-order heat-type equations // J. Theor. Probab., 2000, v. 13, no. 4, 997–1012.
