Welcome to a CEDAR Seminar with Huixia Savannah Wang! She will talk about how she used a tree-based model within the Bayesian framework and data from SHARE to study and evaluate cognitive decline across countries.
Participate on site at Fatmomakke, or online!
Map to venue
Zoom link
Huixia Savannah Wang is a Research Assistant at Umeå School of Business, Economics and Statistics
Cognitive decline is a major challenge in aging populations. Long-term studies give researchers important opportunities to investigate how potentially modifiable factors can influence cognitive health over time. It is however challenging to study cause and effect in these studies. Researchers need to account for factors that change over time and that may affect results, multilevel structure, attrition, and limited empirical support.
This thesis develops and evaluates statistical methods to address these challenges within a Bayesian causal inference framework. The methods use a flexible tree-based model called random-intercept Bayesian Additive Regression Trees (riBART) to account for multilevel structure of the data.
