Department of Biostatistics Seminar/Workshop Series
New Developments in Relative Survival
Janez Stare
Head, Institute of Biomedical Informatics
Ljubljana University, Ljubljana, Slovenia
Friday, April 22, time and place to be determined
Intended Audience: Persons interested in applied statistics, statistical theory, epidemiology
Relative survival techniques are used to compare survival
experience in a study cohort with the one expected should the cohort
follow the background population rates. The techniques are
especially useful when the cause-specific death information is not
accurate or not available as they provide a measure of excess
mortality in a group of patients with a certain disease.
While these methods are based on group comparisons, I will present a transformation approach which
instead gives for each individual an outcome measure relative to
the appropriate background population. The new outcome measure is
easily interpreted and can be analysed using standard survival
analysis techniques. It provides additional information on
relative survival, and gives new options in regression analysis.
One distinctive feature of this approach is that it adjusts
for expected survival before modeling.
The second part of the talk will be devoted to diagnostics for the additive
model,
the most commonly used model for analyzing relative survival data.
Diagnostics
is based on Schoenfeld-like residuals which we have recently introduced.
I will use examples from studies of myocardial infarction and colon cancer
to
illustrate the methods.
Related reference: J Stare, R Henderson, M Pohar (2005): An individual measure of relative survival. JRSS C
54:115-126.
Presenter Information