Level: Intermediate
【Presenter】
Laura Castro-Schilo, JMP Sr. Research Statistician Developer, SAS Institute Inc.
[Announcement summary]
Structural equation modeling (SEM) is a framework that allows one to study the associations between observed and unobserved latent variables. Many applications of SEM use cross-sectional data, and the framework is also very flexible for modeling longitudinal data.
This presentation describes latent growth curve models (LGCMs) as a flexible tool for characterizing growth trajectories over time. We begin by briefly explaining basic concepts of SEM, followed by how we incorporate means into our analyses to test theories of growth. In this study, we illustrate LGCMs by fitting the model to data on individual-reported anxiety and health complaints during the COVID-19 pandemic. Our analysis shows that resilience predicts unique patterns of change in the trajectories of anxiety and complaints.
*Play the video on this site, click on "CC" at the bottom right of the screen, and select "English" to display English subtitles.
If you would like to download the presentation materials and data from this presentation or watch the video with a Japanese transcript, please click here .
Go to each announcement page of Discovery Summit Americas 2021 Presentation.
(Please note that you will be asked to log in to your SAS Profile.)
