Times: Thursday July 14th, 2011 9:00am -4:00pm, Friday July 15th, 9:00am-4:00pm

Location: UBC Campus, Irving K. Barber Centre (IBLC) Room 185

Course Fee: $600 Includes bound copy of comprehensive course notes and refreshments

Instructor

Melania Pintilie is a statistician at the Ontario Cancer Institute and instructor at the Dalla Lana School of Public Health at the University of Toronto. She is also the author of ‘Competing Risks: A practical perspective’ which focuses on the methodology for the analysis of competing risks from an applied perspective.

Workshop description

Survival techniques are well developed and implemented in major statistical software. Yet there are some situations where it may not be appropriate to apply the usual survival methods to the time-to-event analysis. One such situation is where competing risks are present. Competing risk situations can commonly appear when more than one type of event can be observed, but only one of them is of interest. A strong feature of competing risk analysis techniques are in their ability to estimate and model the probability of occurrence of the event of interest. They are therefore very useful to researchers, scientists and clinicians in both the applied health sciences as well as Social Sciences.

Day One 9:00 – 4:00

During the morning session participants will be provided with a review of survival analysis using Cox PH Model and calculation of sample size in survival. Topics covered will include:

• Concepts of time to event analysis when only one type of event is possible to observe
• Assumptions of the Cox proportional hazards model (linearity and proportionality of hazards)
• Methods for checking model assumptions
• Calculation of predicted survival probabilities
• All concepts will be illustrated on real-life examples using R

During the afternoon session, participants will begin to apply concepts presented in the morning to hand-on lab exercises using real-life examples.

Day Two 9:00-4:00

The focus of the second day will be on concepts of time to event analysis in the presence of competing risks. Competing risks situations appears when more than one type of event can be observed, but only one of them is of interest. Topics covered will include:

• Definition and need for different techniques
• Introduction of cumulative incidence function as a means to estimate probability of the event of interest
• Cox proportional hazards and Fine and Gray model
•  Review of methods for checking the assumptions of proportionality of hazards
• Techniques for calculating sample size when competing risks are present

During the afternoon participants will apply these methodologies presented in the morning session through hands-on lab exercises using real-life examples.

Prerequisite

Participants should have a working knowledge of R and a general understanding of statistical modeling and survival analysis.

Additional materials/software requirements  

Participants who wish to bring their own laptop and power cord for use during the workshop will be provided with instructions on how to download R and the necessary R packages approximately one week prior to workshop delivery. Please indicate your interest in this option at time of registration.

Population Data BC has a fleet of laptops for this workshop that will be made available on a first come first serve basis. Please indicate if you wish to reserve a laptop at time of registration

Audience

 The workshop will be of benefit to researchers in health sciences, statisticians working in  clinical settings, scientists concerned with survival designs or analysis in epidemiology, and PhD students.

Register now!

Sponsored by Population Data BC, in partnership with the Division of Continuing Studies, University of Victoria