Navigate Up
Sign In
  • CRM
  • CRM
  • CRM
CRM > English > Activities > Curs 2015-2016 > Competing risks: Concepts, methods and software
Competing risks: Concepts, methods and software
General information

From October 14 to 16, 2015

Course's description

Competing risks: concepts, methods and software
Lecturer: Ronald Geskus, Academic Medical Center, Amsterdam, The Netherlands​ ​​

A competing risks analysis quantifies the occurrence of mutually exclusive event types over time. Furthermore, it is used to study the impact of different factors on this spectrum of event types. Competing risks methods are used increasingly more often in other fields of research. Yet, there is still a lot of confusion with respect to the quantities that can be estimated and their interpretation.

We describe two different approaches to analysis: the multi-state approach and the subdistribution approach. The first is based on the cause-specific hazard, and has a direct extension to Markov multi-state models. Estimation of the cause-specific hazard is completely standard: individuals leave the risk set when they experience a competing event. The cumulative quantity, the cause-specific cumulative incidence, is estimated via the Aalen-Johansen estimator. The subdistribution approach is based on the subdistribution hazard. Under general mechanisms of left truncation and right censoring, an estimator is defined that is based on inverse probability weights. It is used in a product-limit estimator of the cause-specific cumulative incidence that has the surprising property of being algebraically equivalent to the Aalen-Johansen estimator.

In the regression setting, we mainly consider proportional hazards models during the course. For the cause-specific hazard, this is a standard Cox model. The proportional subdistribution hazards model is known as the Fine and Gray model. We explain how the creation of a stacked data set allows for large flexibility in modeling effects on all competing risks in a single analysis.

The course will alternate sessions that are devoted to explanation of the theory with sessions in which the concepts learned can be practiced through exercises, mostly by using the R statistical computing environment. A good working knowledge of survival analysis and R is recommended.

 Scientific coordinators

Guadalupe Gómez  Universitat Politècnica de Catalunya

Montse Rue Universitat de Lleida


Registration fee this course only: 150€ 

Registration fee to this course and the next one (see information below): 200€

Registration includes: Documentation package and coffee breaks​

Deadline for registration: October 4, 2015 

To register to this page's course click the REGISTER BUTTONS AT  THE PAGE TOP AND BOTTOM​
To register to two courses follow the green arrow below​

ATENTION: Reduced registration fee of 200€ for participants also registering to 
Flexible Regression and Smoothing. The GAMLSS packages in R​, November 16 to 18, 2015. By Mikis Statinopoulos, London Metropolitan University
To register at this fee follow the arrow Punter_verd.png (includes registrati​on to both courses)​

​Lodging information

For lodging in the area please click here​

For off-campus and family accommodation click here​​ ​​​
Contact information
If you have any questions please contact: Neus Portet (​)​​