TUES 24 OCT // 8:30 AM – 12:30 PM
Primary Content Focus: Measurement
Secondary Content Focus: Cross-Cutting
Many rehabilitation outcomes evolve over time, which are suited to evaluation using advanced longitudinal and hierarchical statistical models. This course will introduce rehabilitation researchers and clinicians with the rationale and concepts that support the application of individual growth curve modeling. Following the course, learners will be able to appraise existing data for suitability to an individual growth curve model, discuss the relevance of such models with statistical consultants, and plan for data collection in future projects which are suited to modeling outcomes longitudinally.
- Understand the principles that underpin individual growth curve (IGC) analysis
- Discuss measurement issues related to longitudinal analyses
- Identify under what circumstances IGC analysis is appropriate
- Describe a process for examining longitudinal data and determining a best-fit trajectory
- Describe the process for evaluating covariate associations with trajectory parameters
Allan Kozlowski, PhD, BSc (PT)
Mary Free Bed Rehabilitation Hospital
Keith Lohse, PhD
Allan J. Kozlowski, PhD, BSc (PT), an expert in rehabilitation medicine, is Assistant Professor in the Department of Epidemiology and Biostatistics in the Michigan State University College of Human Medicine, and the Director of Outcomes Research in the John F. Butzer Center for Research & Innovation at Mary Free Bed Rehabilitation Hospital. The role is a joint appointment by Mary Free Bed and the College. He received his BSc in physical therapy in 1991 and his PhD in Rehabilitation Sciences in 2010, both from the University of British Columbia. He practiced as a physical therapist and rehabilitation manager in work disability prevention before completing his doctorate in Rehabilitation Sciences. Dr. Kozlowski completed his postdoctoral fellowship at the Center for Rehabilitation Outcomes Research at Rehabilitation Institute of Chicago and the Center for Healthcare Studies at Northwestern University, in which he constructed individual growth models for FIM Instrument scores for persons with spinal cord injuries and traumatic brain injuries. Prior to his current position, he expanded a powered exoskeleton research program examining device usability for persons with spinal cord injury and multiple sclerosis. In his current role, Dr. Kozlowski is leading an effort to model rehabilitation outcomes across post-acute care services for a variety of patient populations. Dr. Kozlowski has authored more than 20 articles on topics including modeling of rehabilitation outcomes as individual trajectories of change, psychometric properties of measurement instruments, and exoskeleton-assisted walking. He has also instructed courses in longitudinal modeling, measurement in clinical practice, and physical therapy clinical skills.
Keith Lohse received a joint PhD in neuroscience, cognitive science, and psychology from the University of Colorado and completed his post-doctoral training in rehabilitation science at the University of British Columbia. Dr. Lohse has more than 3o peer-reviewed manuscripts published in biomedical and psychology journals and has been invited to lead workshops on longitudinal data analysis. He also served as an ad-hoc reviewer for 24 scientific journals, and currently serves on the editorial board for the Journal of Motor Learning and Development. As the Director of the Rehabilitation Informatics Laboratory at Auburn University, Dr. Lohse and his team are exploring techniques for optimizing data collection, management, and analysis rehabilitation science and clinical practice. He has helped develop tools for the management and analysis of longitudinal data, and implemented large-scale meta-analytic research pooling data from hundreds of randomized controlled trials. Dr. Lohse has also pursued advanced training in statistical analysis and data science, specifically multi-level statistical models and their application to rehabilitation.