Empirical and Poisson processes on classes of sets or functions too large for central limit theorems |
| |
Authors: | R M Dudley |
| |
Institution: | (1) Dept. of Mathematics, Massachusetts Institute of Technology, Room 2-245, 02139 Cambridge, Mass., USA |
| |
Abstract: | Summary Let P be the uniform probability law on the unit cube I
d in d dimensions, and P
n
the corresponding empirical measure. For various classes of sets AI
d
, upper and lower bounds are found for the probable size of sup {¦P
n
–P) (A)¦ A }. If is the collection of lower layers in I
2, or of convex sets in I
3, an asymptotic lower bound is ((log n)/n)
1/2(log log n)––1/2 for any >0. Thus the law of the iterated logarithm fails for these classes.If >0, is the greatest integer <, and 0, let be the class of all sets {x
d
f(x1,...,x
d-1)} where f has all its partial derivatives of orders bounded by K and those of order satisfy a uniform Hölder condition ¦D
p
(f(x)–f(y))¦K¦x –y¦
–. For 0<n–/(d–1+) for a constant = (d,)>0. When = d-1 the same lower bound is obtained as for the lower layers in I
2 or convex sets in I
3. For 0<d – 1 there is also an upper bound equal to a power of log n times the lower bound, so the powers of n are sharp.This research was partially supported by National Science Foundation Grant MCS-79-04474 |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|