Matthias Studer
@matstud.bsky.social
Social Statistician, Phd in Socioeconomics, #lifecourse, #SequenceAnalysis, University of Geneva.
Step-by-step tutorial on using the method (CLARA) in R with the WeightedCluster package for sequence analsyis for large databases : cran.r-project.org/web/packages...
Short R Tutorial: Sequence Analysis Typologies for Large Databases
cran.r-project.org
March 21, 2025 at 12:41 PM
Step-by-step tutorial on using the method (CLARA) in R with the WeightedCluster package for sequence analsyis for large databases : cran.r-project.org/web/packages...
Sequence Analysis for Large Databases, Working paper (open access): dx.doi.org/10.12682/liv...
Sequence Analysis for Large Databases | Centre LIVES
dx.doi.org
March 21, 2025 at 12:41 PM
Sequence Analysis for Large Databases, Working paper (open access): dx.doi.org/10.12682/liv...
The procedure provides robust estimates for an association of interest.
It also identifies central and borderline trajectories within each cluster.
The method is illustrated through a study of healthcare use trajectories in a Swiss cohort of diabetic patients.
It also identifies central and borderline trajectories within each cluster.
The method is illustrated through a study of healthcare use trajectories in a Swiss cohort of diabetic patients.
December 19, 2024 at 9:51 PM
The procedure provides robust estimates for an association of interest.
It also identifies central and borderline trajectories within each cluster.
The method is illustrated through a study of healthcare use trajectories in a Swiss cohort of diabetic patients.
It also identifies central and borderline trajectories within each cluster.
The method is illustrated through a study of healthcare use trajectories in a Swiss cohort of diabetic patients.
We propose a new procedure to take sampling uncertainty based on bootstraps. In each bootstrap, a new typology and regression are estimated. The bootstrap estimates are then combined using a meta-analysis framework.
December 19, 2024 at 9:51 PM
We propose a new procedure to take sampling uncertainty based on bootstraps. In each bootstrap, a new typology and regression are estimated. The bootstrap estimates are then combined using a meta-analysis framework.
#SequenceAnalysis is often used to create a typology of trajectories. This typology is then used in regressions to study the association between trajectories and covariates.
By doing so, sampling uncertainty, which affects both the typology and the regressions, is ignored.
By doing so, sampling uncertainty, which affects both the typology and the regressions, is ignored.
December 19, 2024 at 9:51 PM
#SequenceAnalysis is often used to create a typology of trajectories. This typology is then used in regressions to study the association between trajectories and covariates.
By doing so, sampling uncertainty, which affects both the typology and the regressions, is ignored.
By doing so, sampling uncertainty, which affects both the typology and the regressions, is ignored.
This article develops and reviews methods for the creation of sequence analysis typologies in large databases, which rapidly faces computational issues. It proposes an extension of the CLARA clustering algorithm and discusses three approaches to measure the quality of the clustering.
December 4, 2024 at 4:19 PM
This article develops and reviews methods for the creation of sequence analysis typologies in large databases, which rapidly faces computational issues. It proposes an extension of the CLARA clustering algorithm and discusses three approaches to measure the quality of the clustering.