Target audience

Anyone working with event-time data, especially if individual event times often fall outside of the follow up time. E.g.

• Clinical: time to relapse, time to (re-)hospitalization, time to death
• Economic: time to employment
• Industry: time to replacement/repair (optimization), time to purchase

Description

Analyzing time to an event (disease recurrence, death, employment, breakdown of machinery, first purchase,…) takes an important place in many fields. In many cases, however, the event of interest only occurs for a subset of observations. For the others, we only know it didn’t happen within the observed timeframe. This incomplete information (some observations are ‘censored’), raises difficulties that makes time-to-event analysis a field on its own.

For example, what is the meaning of the average time to employment, if a large proportion of your sample is still unemployed? How to deal with a patient who died before relapse, when analyzing time to relapse? Can we infer conclusions for those we followed for 1 year, based on what we see in those we follow for 5 years?

It is important to acknowledge these difficulties without overlooking implicit assumptions while in the meantime leveraging the available information to its fullest extent.

This course offers an introduction to time-to-event analysis, starting with the basic concepts with a focus on explicitely stating and evaluating underlying assumptions. Descriptive techniques (Kaplan Meier) and regression model (Cox Proportional Hazard models and parametric models) are extensively discussed before exploring competing risks (e.g. people who retire before finding a new job) and multi-state models (e.g. chronic illness vs acute illness vs death).

Theoretical sessions are alternated with PC-practicals where the theory is applied to real datasets using R-software. The code will be provided, to have the focus on understanding theory and code, rather than writing the code.

Course prerequisites

Intermediate knowledge of statistical principles and some experience with interpreting regression models (linear regression, logistic regression,…). Basics of using R (code is provided, but you have to be able to read and understand it).

Exam / Certificate

There is no exam connected to this module. If you attend all four sessions you will receive a certificate of attendance via e-mail at the end of the course.

Type of course

This is an on campus course. We offer blended learning options if, exceptionally, you can't attend a class on campus.

Schedule

Two full days in May 2023: Monday May 22 and Tuesday May 23, 2023, from 9 am to 12 pm and from 1 pm to 4 pm

Venue

UGent, Faculty of Science, Campus Sterre, Krijgslaan 281, Ghent. Building S9, 3rd floor, pc room 3.1 (Konrad Zuse).

Teacher

Dries Reynders studied Physics and Statistical Data Analysis at Ghent University.

He is an experienced teacher and is, in that role, well trained in explaining the link between mathematics and the reality it describes. Currently, he works as statistical consultant for the Stat-Gent consortium.

Course material

Acces to slides and code for the practical sessions

Fees

A different price applies, depending on your main type of employment.

*If two or more employees from the same company enrol simultaneously for this course a reduction of 20% on the module price is taken into account, starting from the second enrolment.

Register

Register for this course

UGent PhD students

As UGent PhD student you can incorporate this 'transferable skills seminar: research & valorization' in your Doctoral Training Program (DTP). To get a refund of the registration fee from your Doctoral School (DS) please follow these strict rules and take the necessary action in time. The deadline to open a dossier on the DS website (Application for Registration) for this course is April 21, 2023.

Opening a dossier with your DS does not mean that you are enrolled for the course with our academy. You still need to enrol via the registration form on this site.

It is you or your department that pays the fee first to our academy. The Doctoral School refunds that fee to you or your department once the course has ended.