This research examines probability limits over classes of sets and functions. Empirical measures can be applied to sets or to functions to define empirical processes. Earlier results in empirical process theory established that convergence in distribution to a Gaussian holds uniformly for certain classes of sets and functions. This research seeks to find larger classes of sets for which statistical functionals are differentiable and therefore can be approximated by a process with this convergence property, plus a remainder of lower order.

Agency
National Science Foundation (NSF)
Institute
Division of Mathematical Sciences (DMS)
Application #
9108339
Program Officer
Sallie Keller-McNulty
Project Start
Project End
Budget Start
1991-08-01
Budget End
1994-01-31
Support Year
Fiscal Year
1991
Total Cost
$89,248
Indirect Cost
Name
Massachusetts Institute of Technology
Department
Type
DUNS #
City
Cambridge
State
MA
Country
United States
Zip Code
02139