Online Program Home
My Program

Abstract Details

Activity Number: 375
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract #320252
Title: Modified Kolmogorov-Smirnov Test for Conditional Survival and its Application
Author(s): Yueh Wang* and Hung Hung
Companies: and National Taiwan University
Keywords: Kolmogorov-Smirnov ; conditional ; survival analysis ; population cure

In cancer epidemiology, the issue of finding the time to population cure, which is an important index for government to make health policies, has not been well developed. The time to population cure means the follow-up time after which the cancer population and general population have equal survival behavior. This research aims to find the time to cure by using a series of testing procedure. We begin with asking 2 questions, first we ask "does the time to cure exist in patient population?", if the first question has answer "yes", then we ask the second question "what is the time to cure?". We referred to the modified Kolmogorov-Smirnov statistic proposed by Fleming and Harrington (1980), and developed the conditional version of modified Kolmogorov-Smirnov testing procedure. We used the intersection-union test to answer the first question, and sequential test to answer the second question. Breast cancer and colorectal cancer population data in Taiwan cancer registry were used as real data application. There is no time to population cure in breast cancer population, and the follow-up time of 11 year is the time to cure of colorectal cancer population in Taiwan.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association