- August 6, 2020 from 12:00-1:00pm
- Please RSVP by emailing Lisa Maturo at Lisa.M.Maturo@christianacare.org.
- Please include your full name, email address, and institution/organization.
- We will provide instructions on obtaining CME credit for attendance.
This presentation will provide an introduction to Mixture and Growth Mixture Modeling. These methods are useful for identifying unobserved homogeneous groups of individuals within a larger heterogenous sample. Cross sectionally, Mixture Modeling can be used to identify classes of individuals based on observed variables and latent traits, and then use that information within larger and more complicated statistical models. With longitudinal data, these models are able to identify subsets of classes based on their developmental trajectories and this information can be used in larger models. With the broad availability of R and ‘user-friendliness’ of MPlus, these models will continue to become more accessible for applied researchers. The goal of this presentation is to provide a conceptual overview of these methods and identifying when applications of them would be useful.
Meet the Speaker
Ryan Pohlig is the Director of the Biostatistics Core and a faculty member in Epidemiology Program for the College of Health Sciences at the University of Delaware. He obtained his Ph.D. from Pitt in 2013 in research methodology, with a primary focus on statistics. He has participated in research from a wide range of fields including health sciences, psychology, biomechanics, social work, and law, leading to over 80 publications. His interests include structural equation modeling, mixed modeling, mediation and moderation analyses, and study design.
This activity has been approved for AMA PRA Category 1 Credit