PřF:Bi8678 Applied survival analysis - Course Information
Bi8678 Applied survival analysis
Faculty of Scienceautumn 2017
- Extent and Intensity
- 2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: graded credit.
- Teacher(s)
- doc. Mgr. Zdeněk Valenta, M.Sc., M. S., Ph.D. (lecturer)
RNDr. Tomáš Pavlík, Ph.D. (lecturer) - Guaranteed by
- prof. RNDr. Ladislav Dušek, Ph.D.
RECETOX – Faculty of Science
Contact Person: RNDr. Tomáš Pavlík, Ph.D.
Supplier department: RECETOX – Faculty of Science - Timetable
- Mon 18. 9. to Fri 15. 12. Wed 11:00–14:50 F01B1/709
- Prerequisites
- Bi5045 Biostatistics for Computational Biology
- Course Enrolment Limitations
- The course is offered to students of any study field.
- Course objectives
- The goals for the course are the following:
- Introducing the topic of Survival Analysis, indicating its connection with Clinical Trials where it is used as a main analytical tool with the emphasis on understanding Clinical Trials design and an appropriate choice of optimal data analytic tools from the design point of view;
- Familiarise the students with elementary concepts in Survival Analysis, such as right censoring, left censoring, interval censoring and truncation, survival function, risk (hazard) function, understanding the difference between median or mean survival time vs. median or mean or median residual lifetime;
- Make the students familiar with three classes of models used in Survival Analysis, namely the classes of nonparametric, parametric and semi-parametric models for the hazard function, including its main representatives;
- Emphasis will also be given on understanding restrictive assumptions that need to be satisfied in order to justify the use of particular Survival Analysis models in data analysis;
- Another goal is the ability to correctly interpret the analyses results in the context of medical hypotheses being tested;
- The last but not least, the students will have practical hands-on experience with analysing survival data in the R environment (R-studio) - Learning outcomes
- After completion of the course, student:
- knows the principles of censoring;
- can define survival function, hazard function, and cumulative hazard function;
- understands the difference between median and mean survival time and life expectancy;
- is able to construct Kaplan-Meier estimate of the survival function;
- is able to construct life-table estimate of the survival function;
- is able to construct Nelson-Aalen estimate of the cumulative hazard function;
- can add confidence interval to the nonparametric estimates;
- understands the principles of maximum likelihood estimation in survival analysis;
- is able to construct the likelihood function for survival data;
- can assess the assumption of exponential or Weibull probability distribution;
- can define proportionality of hazard functions;
- is able to apply Mantel-Haenszel logrank test;
- knows an alternative test in the case of nonproportionality of hazards;
- is able to use test for more than two groups of subjects;
- understands the relationship between overall, expected, and relative survival;
- knows the most used methods for expected survival estimation;
- understands the principles of statistical cure;
- is able to detect statistical cure using interval-specific relative survival;
- is able to explain the meaning of regression methods in survival analysis;
- can define hazard ratio and baseline hazard;
- is able to formulate proportional hazards model for survival data;
- is able to formulate accelerated failure time model for survival data;
- is able to formulate Cox proportional hazards model;
- understands the meaning of regression coefficients in survival model;
- knows maximum likelihood estimation of the regression coefficients;
- knows methods for nonparametric estimation of the baseline hazard;
- is able to formulate, explain and apply Aalen' additive model for the hazard function;
- is able to formulate, explain and apply Grays' flexible model for the hazard function with time-varying regression coefficients;
- is able to formulate, explain and apply Cox-Aalen additive-multiplicative model for the hazard function - Syllabus
- Basic terms in survival analysis
- Nonparametric estimates
- Parametric estimates
- Methods for comparing survival functions
- Relative survival
- Regression models in survival analysis
- Cox proportional hazards model
- Aalen's additive model
- Gray's flexible time-varying coefficients model
- Cox-Aalen multiplicative-aditive model
- Literature
- KLEIN, John P. and Melvin L. MOESCHBERGER. Survival analysis : techniques for censored and truncated data. New York: Springer, 1997, xiv, 502. ISBN 0387948295. info
- MARUBINI, Ettore and Maria Grazia VALSECCHI. Analysing survival data from clinical trials and observational studies. Chichester: John Wiley & Sons, 1995, xvi, 414. ISBN 0471939870. info
- Teaching methods
- lectures, class discussion, group project
- Assessment methods
- one written test (30 questions, each contributing 1 point, 25 points needed to pass), final (group) project, oral examination in case of failing the written test.
- Language of instruction
- Czech
- Further comments (probably available only in Czech)
- Study Materials
Information on the extent and intensity of the course: výuka bude 1 x za 2 týdny, první výuka proběhne 5.10.2016.
- Enrolment Statistics (autumn 2017, recent)
- Permalink: https://is.muni.cz/course/sci/autumn2017/Bi8678