Rates of growth and sample moduli for weighted empirical processes indexed by sets

SummaryProbability inequalities are obtained for the supremum of a weighted empirical process indexed by a Vapnik-Červonenkis class C of sets. These inequalities are particularly useful under the assumption P(∪{C∈C:P(C)<t})»0 as t»0. They are used to obtain almost sure bounds on the rate of growth of the process as the sample size approaches infinity, to find an asymptotic sample modulus for the unweighted empirical process, and to study the ratio Pn/P of the empirical measure to the actual measure.

[1]  G. Bennett.  Probability Inequalities for the Sum of Independent Random Variables , 1962 .

[2]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[3]  W. Uhlmann.  Vergleich der hypergeometrischen mit der Binomial-Verteilung , 1966 .

[4]  S. M. Samuels,et al.  Monotone Convergence of Binomial Probabilities and a Generalization of Ramanujan's Equation , 1968 .

[5]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[6]  Richard M. Dudley,et al.  Sample Functions of the Gaussian Process , 1973 .

[7]  Steven Orey,et al.  Sample Functions of the $N$-Parameter Wiener Process , 1973 .

[8]  W. Stout.  Almost sure convergence , 1974 .

[9]  E. Csáki.  The law of the iterated logarithm for normalized empirical distribution function , 1977 .

[10]  R. Dudley.  Central Limit Theorems for Empirical Measures , 1978 .

[11]  Martien C. A. van Zuijlen,et al.  Properties of the Empirical Distribution Function for Independent Non- Identically Distributed Random Vectors , 1978 .

[12]  J. Wellner.  Limit theorems for the ratio of the empirical distribution function to the true distribution function , 1978 .

[13]  V. Vapnik,et al.  Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations , 1982 .

[14]  J. Wellner,et al.  Limit Theorems and Inequalities for the Uniform Empirical Process Indexed by Intervals , 1982 .

[15]  D. Pollard.  A central limit theorem for empirical processes , 1982, Journal of the Australian Mathematical Society. Series A. Pure Mathematics and Statistics.

[16]  Winfried Stute,et al.  THE OSCILLATION BEHAVIOR OF EMPIRICAL PROCESSES , 1982 .

[17]  W. Stute.  A Law of the Logarithm for Kernel Density Estimators , 1982 .

[18]  Jon A. Wellner,et al.  Strong limit theorems for oscillation moduli of the uniform empirical process , 1983 .

[19]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[20]  D. Pollard.  Convergence of stochastic processes , 1984 .

[21]  K. Alexander,et al.  Probability Inequalities for Empirical Processes and a Law of the Iterated Logarithm , 1984 .

[22]  Winfried Stute,et al.  The Oscillation Behavior of Empirical Processes: The Multivariate Case , 1984 .

[23]  D. Freedman,et al.  Asymptotics of Graphical Projection Pursuit , 1984 .

[24]  E. Giné,et al.  Some Limit Theorems for Empirical Processes , 1984 .

[25]  J. Yukich.  Laws of large numbers for classes of functions , 1985 .

[26]  J. Kiefer.  Iterated Logarithm Analogues for Sample Quantiles When P n ↓0 , 1985 .

[27]  Kenneth S. Alexander,et al.  Sample Moduli for Set-Indexed Gaussian Processes , 1986 .