Applied statistics III – Survival analysis
Philippe Wagner, Statistician email@example.com
Jonas Björk, professor of Epidemiology, firstname.lastname@example.org
The course is intended for doctoral students at the medical faculty with research projects suited for survival analysis. The course is, conditional on availability, also intended for post-doctoral students and others with a special interest in survival analysis at the medical faculty and for doctoral students, post-doctoral students and others with special interest outside of the medical faculty. Although the latter may consitute at most 50% of course participants. All course attendants must have prior knowledge in applied statistics corresponding to course levels I and II. Access to and substantial skills in a statistical software packages are also required: SPSS, SAS, STATA, R or equivalent.
Week 21, 2021
Lund - Lecture room will be announced to the students before course start.
b. Typical situations suitable for survival analysis
c. Study design
2. Description of data
a. The survival function
b. Life tables
c. The Kaplan-Meier estimate
3. Analyses of group differences
a. The Kaplan-Meier estimate and confidence interval
b. The log-rank test
4. Analyses of group differences – in depth
• Spurious effects (confounding)• Stratified log-rank test• Hazards• Cox regression• Adaptation of the Cox model• Log-minus-log-plot• Schoenfeld residuals
5. Cox-regression – more theory
• Sampling from the risk set – similarities with nested-case control design
• Similarities between hazard rates and incidence rate ratio
• Similarities between Cox and Poisson regression
6. Design and interpretation aspects – specialisation
- Competing risks- Confounding, mediation and moderation of effects- Non-linear effects- Time-varying covariates and time-varying effects
Articles and additional course material will be announced before and during the course.
The course will be held in English and requires active participation and access to laptop with installed statistical package that you are familiar with from earlier courses (SPSS, STATA, SAS, R or equivalent). More information will be provided before the course start.