Since its introduction in the social sciences by Andrew Abbott in the nineties, sequence analysis has been increasingly used to study trajectories and is considered a key method for life-course research. It encloses a broad set of methods aiming to analyze trajectories from a holistic perspective ranging from visualization to explanatory methods.
A standard application of sequence analysis typically follows three steps. First, it starts by using visualization techniques to describe the trajectories according to three key dimensions for life course research, namely the timing (when a situation occurs), the duration (for how long last a situation) and the sequencing of the situation encountered in the processes. Second, it relies on cluster analysis to create a typology of the observed trajectories, aiming to identify recurrent patterns or, in other words, typical successions of states through which the trajectories run. Finally, it uses regressions to understand how sociodemographic characteristics are linked to each type of trajectories. The typology can also be used to describe how an outcome, such as income, is linked with a previous trajectory.
This presentation provides a general introduction to sequence analysis and discusses some of its uses in the social sciences by taking examples from education and school-to-work transition studies in Switzerland. Sequence analysis has also raised different concerns and criticisms. Among others, it requires the choice of a distance measure, and it relies on a simplification of the sequences, which might affect subsequent analyses. The presentation further aims to highlight key methodological issues, some of the more recent developments to address them and introduces some less well-known but useful techniques.
Click here to download the presentation of the lecture (PDF)