Student Seminar Series - September 13, 2004
University of Minnesota
School of Statistics
College of Liberal Arts
Comparison
of Kaplan-Meier-type and Self-Consistent Estimators of the Bivariate
Survivor Function
Luu Pham
Monday, September 13, 2004
10:00 AM, TBA
Ford Hall
Minneapolis, East Bank Campus
Refreshments at 9:30 AM
300 Ford Hall
Abstract
Many non-parametric estimators of the bivariate survival function
for right-censored data have been proposed. One approach is an explicit
estimator derived as a product-limit or Kaplan Meier-type estimator,
which produces a non-negligible proportion of negative mass points. A
second approach is an implicit estimator which is based on the solution
to Efron's Self-Consistency equation, and depends on bandwidths. I
review the univariate estimators, and provide descriptions of the
computation of the bivariate estimators. Simulation study results
follow. A distance measure is proposed for comparing the estimators.