The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
|
Activity Number:
|
569
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2012 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #306147 |
|
Title:
|
Hoeffding-Type and Bernstein-Type Inequalities for Right-Censored Data
|
|
Author(s):
|
Yair Goldberg*+ and Michael Kosorok
|
|
Companies:
|
Haifa University and The University of North Carolina at Chapel Hill
|
|
Address:
|
Mount Carmel,, Haifa, _, 31905, Israel
|
|
Keywords:
|
concentration inequalities ;
right censored data ;
inverse probability weighting ;
finite sample bounds
|
|
Abstract:
|
The Hoeffding and the Bernstein inequalities bound the probability of the deviation of the sample mean from its expectation, for i.i.d. random variables. When the data is subject to right-censoring, only a lower bound of the failure time is given for the censored observations. Consequently, the sample mean of the failure time is no longer an unbiased estimator of the mean. An inverse-probability-weighted estimator for the truncated mean can be shown to be unbiased when the failure time is independent of censoring. Here we present Hoeffding- and Bernstein-type inequalities for the deviation of the inverse-probability-weighted estimator from its expectation. These results are of interest, since unlike the sample mean, the inverse-probability-weighted estimator is not a function of a sum of i.i.d. random variables.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.