Far East Journal of Theoretical Statistics
Volume 19, Issue 2, Pages 203 - 217
(July 2006)
|
|
INFORMATIVE CENSORING IN SURVIVAL ANALYSIS AND APPLICATION TO
ASTHMA
Christel Castelli (France), Philippe Saint-Pierre (France) and Jean-Pierre Daures (France)
|
Abstract: In epidemiological studies, survival
analyses are often carried out in order to better understand the onset of an
event. The data have the particularity of being incomplete due to the different
censoring phenomena. Traditional methods make the hypothesis of censoring being
independent from the event, which may be a source of bias in certain
pathologies. The Inverse Probability of Censoring Weighted (IPCW) method adapts
the Kaplan-Meier estimators and the Cox partial likelihood method to cases, with
non independent censoring. This method uses the information resulting from
censoring to modify the contribution of individuals in the estimators. This
method is applied to asthma, a case in which therapists believe that patients
lost to follow-up are patients who are in otherwise good health, and do not feel
the necessity to consult a doctor (informative censoring). |
Keywords and phrases: Cox proportional hazards model, informative censoring, asthma. |
|
Number of Downloads: 311 | Number of Views: 774 |
|