Summary
We compare various kind of independence tests based on samples with random size, in order to provide practitioners with some guidance for their choice based on approximate Bahadur efficiency. Such results are obtained for a wide class of distributions of the random index; the efficiency slopes of the statistics we consider are then expressed in terms of the parameters of these same distributions.
Similar content being viewed by others
References
Allen, J., Beekman, J. (1967), On the distribution of the M. Kac statistic.Ann. Math. Stat., 38, 6, 1919–1923.
Bahadur, R. R. (1960), Stochastic comparison of tests.Ann. Math. Stat., 31, 276–295.
Bahadur, R. R. (1971),Some Limit Theorems in Statistics, Philadelphia: SIAM.
Bajorski, P. (1987), Local Bahadur optimality of some rank tests of independence.Stat. and Prob. Letters, 5, 6, 255–262.
Beghin, L. (2000), Weak convergence of some randomly indexed empirical processes, Technical Reports Dipart. di Stat. Prob. e Stat. Appi., Univ. di Roma, «La Sapienza», Serie A — Ricerche, 28, (submitted for publication).
Conti, P. L., Nikitin, Ya. Yu. (1999), Asymptotic efficiency of independence tests based on Gini’s rank association coefficient, Spearman’s footrule and their generalizations.Commun. Statist. — Theory Meth., 28, 2, 453–465.
Csörgo, M. (1968), On the strong law of large numbers and the central limit theorems for martingales.Trans. Am. Math. Soc., 131, 259–275.
Csörgo, M. (1972), Distribution results for distance functions based on the modified empirical distribution function of Kac.Ann. Inst. Stat. Math., 24, 101.
Csörgo, S. (1981), Strong approximations of empirical Kac processes.Ann. Inst. Stat. Math., 33, 3, 417–423.
Dudley, R. M. (1999),Uniform Central Limit Theorems, New York: Cambridge Studies in Adv. Mathem., Cambridge Univ. Press.
Farlie, D. J. (1960), The performance of some correlation coefficients for a general bivariate distribution.Biometrika, 47, 307–323.
Gnedenko, B. V., Korolev, V. Yu. (1996),Random Summation: Limit Theorems and Applications, Boca Raton-New York-London-Tokyo: CRC Press.
Gumbel, E. J. (1958), Distributions à plusieurs variables dont les marges sont données.C.R. Acad. Sci., 246, 2717–1719.
Kac, M. (1949), On deviations between theoretical and empirical distributions.Proc. Nat. Acad. Sci. U.S.A., 35, 252–257.
Klaassen, C. A., Wellner, J. A. (1992), Kac empirical processes and the bootstrap.Proc. of the Eight Intern. Conf. on Prob. in Banach Spaces, 411–429, (eds. M. Hahn and J. Kuelbs) New York: Birkäuser.
Marcus, M. B., Shepp, L.A. (1971), Sample behaviour of Gaussian processes.Proc. Sixth Berkeley Symp. Math. Stat. Prob., 2, 423–442.
Morgenstern, D. (1956), Einfache Beispiele zweidimensionaler Verteilungen.Mitt. Mathem. Statist., 8, 234–235.
Nikitin, Ya. Yu. (1981), Limit distributions and comparative asymptotic efficiency of the Kolmogorov-Smirnov statistics with random index.Journal of Soviet Math., 2, 1042–1049.
Nikitin, Ya. Yu. (1995),Asymptotic Efficiency of Nonparametric Tests, New York: Cambridge Univ. Press.
Nikitin, Ya. Yu., Pankrashova, A. (1990), Bahadur efficiency and local asymptotic optimality of certain nonparametric tests of independence.Journal of Soviet Math., 52, 2942–2955.
Paulauskas, V. I. (1972), On the sum of a random number of multidimensional random vectors.Litov. Mat. Sb., 12, no. 2, 109–131, in Russian.
Suzuki, G. (1972), Distribution of Kac-statistics.Ann. Inst. Stat. Math., 24, 415–421.
Van der Vaart, A. W., Wellner, J. A. (1996),Weak Convergence and Empirical Processes, New York-Berlin-Heidelberg: Springer-Verlag.
Wieand, H. S. (1976), A condition under which the Pitman and Bahadur approaches to efficiency coincide.Ann. Stat., 4, 1003–1011.
Author information
Authors and Affiliations
Additional information
Research partially supported by RFBR (grant no. 99-01-0724) and ICER (Turin).
Rights and permissions
About this article
Cite this article
Beghin, L., Nikitin, Y.Y. Approximate asymptotic Bahadur efficiency of independence tests with random sample size. J. Ital. Statist. Soc. 8, 1 (1999). https://doi.org/10.1007/BF03178938
DOI: https://doi.org/10.1007/BF03178938