VIRTUAL EVENT: The link between previous life trajectories and a later life outcome
In this webinar, Matthias Studer will discuss how to investigate the link between previous life trajectories and a later life outcome using a feature selection approach.

Several studies have investigated the link between a previous trajectory and a given outcome later on in life.
However, trajectories are complex and it is not straightforward to identify which aspects of the trajectories are relevant in terms of both prediction and testing specific theories.
In this talk, Matthias will discuss work conducted with Danilo Bolano, in which they propose an innovative approach based on sequence analysis and data mining feature selection algorithms.
Furthermore, Matthias will discuss the use of two feature selection approaches, namely random forest (Boruta) and a LASSO (Stability Selection).
The proposed approach is illustrated through a study that explores the effects of family and work trajectories between ages 20 and 40 on women’s earnings in midlife.
QSS seminar series
In this weekly Quantitative Social Science (QSS) seminar series, speakers present research that falls under the broad umbrella of quantitative social science.
Links
Senior Researcher
the University of Geneva, The Swiss National Centre of Competence in Research LIVES (NCCR LIVES)
Matthias is a recognised specialist in the quantitative analysis of longitudinal data and more specifically in sequence analysis.
Further information
Ticketing
Pre-booking essential
Cost
Free
Open to
All
Availability
Yes