Rehabilitation researchers and clinicians often deal with outcomes that evolve over time and are not suited to binary categorization of pre- post-assessments, as is common in other areas of medicine and healthcare. This course will build on our previously offered introduction to modeling longitudinal outcomes in a lecture and practical workshop format. Advanced topics include methods to assess data and model structure visually, statistically, and conceptually; and to fit more complex models and outcome types. While not a prerequisite, course participants will benefit from having a working knowledge of the introductory course content and of the R environment.
Describe the structure of curvilinear and non-linear (e.g., negative exponential) models
Examine relationships of data to model fit by examining data patterns over time
Discuss the use of fixed and time-varying covariates in curvilinear models
Fit models for curvilinear and non-linear (e.g., negative exponential) continuous outcomes in the R statistical environment