Curso Analytical Methods for Competing Events

Description:

Time to event data with two or more types of endpoints are found in many epidemiological settings and are commonly analyzed using methods for competing risks. A competing risk is defined as an endpoint that precludes the observation of another event. The most common approach for the analysis of data with competing risks is to treat the times for one of the endpoints as censored observations for the other. This approach is closely linked to the use of semi-parametric models for the analysis of cause-specific hazards under a proportionality assumption. In this course, we will describe an application of a mixture of parametric survival distributions for the analysis of time to event data with competing risks. We treat competing events as distinct outcomes in a mixture of parametric survival distributions and use the three-parameter generalized gamma distribution to summarize the times to events. An alternative method for the analysis of competing risks is to semi-parametrically model the sub-hazards in unexposed and in exposed individuals of the cumulative incidences as proportional and to test whether they are different from 1. In this course, we will show the consequences of assuming proportionality of subhazards and indicate the limitations of that approach to appropriately describe effects of exposures on competing risks.

Instructor:

Alvaro Muñoz, Ph.D.
Professor of Epidemiology
Johns Hopkins Bloomberg School of Public Health
Baltimore, MD, USA

Who?

The course Analytical Methods for Competing Events is addressed to professional or academics statisticians and researchers who are interested in being introduced to the use of these methods.

Prerequisites:

It is expected that participants are familiar with survival analysis at an intermediate level including familiarity with proportional hazards regression. The laboratories will use SAS but programs to run the laboratories will be provided
SEA informs that previously there are two complementary courses: Introduction to the SAS® system on October from 24th to 27th; and Statistical Modelling with SAS® on November from 28th to 30th and December 1st.

Program of Lectures and Laboratories:

December 13

• 10:00 – 11:50: Lecture 1
  Analytical methods for incomplete observations in cohort studies.
  Completing the missing information due to censoring and late entries.
• 12:10 – 14:00 Lecture 2
  Measures to compare time-to-event data: relative percentiles and relative hazards; Taxonomy of hazard functions of the general gamma distribution and Parametric survival analysis based on the general gamma distribution
Reference: Cox C, Chu H, Schneider MF, Muñoz A. Parametric Survival Analysis and Taxonomy of Hazard Functions for the Generalized Gamma Distribution. Stat Med 2007;26:4352-74.

• 16:00 – 18:00 Laboratory
  redistribution of right censored; right censored and late entries; competing risks with right censoring and laboratory on parametric models

December 14

• 10:00 – 11:50: Lecture 1
  Basic concepts in competing risks: cause-specific hazard functions; sub-hazards of the cumulative incidences; mixture and conditional hazards. Proportionality of the cause-specific hazard functions and of the subhazard functions
• 12:10 – 14:00 Lecture 2
  Inference for mutually exclusive competing events through a mixture of generalized gamma distributions.
References:
Cole SR, Li R, Anastos K, Detels R, Young M, Chmiel JS, Muñoz A.Accounting for leadtime in cohort studies: evaluating when to initiate HIV therapies.Stat Med 2004;23:3351-63.
Checkley W, Brower RG, Muñoz A. Inference for mutually exclusive competing events through a mixture of generalized gamma distributions. Epidemiology 2010;21:557-65.

• 16:00 – 18:00 Laboratory
  Analysis of the data in Table 10.1 of Marubini et al. using mixtures of generalized gamma distributions.

December 15

• 10:00 – 11:50: Lecture 1
  Comparison of methods for the analysis of competing risks data.
• 12:10 – 14:00 Lecture 2
  Non-proportionality of sub-hazards in the competing events framework and tethering of the relative sub-hazards.
Reference:
Muñoz A, Abraham A, Matheson M, Wada N.Non-proportionality of sub-hazards in the competing events framework. Abstract of invited presentation at conference on risk assessment and evaluation of predictions;October 12-14, 2011; Silver Spring. MD, USA.
http://brac.umd.edu/~Risk2011/Main.htm

• 16:00 – 18:00 Laboratory
  Analysis of data using relative sub-hazards as the measure of interest in both the settings of proportional and non-proportional sub-hazards
•  
• Más información en:http://sct.uab.cat/estadistica/es/content/curso-analytical-methods-competing-events