The Consortium for Advanced Research Methods and Analysis (CARMA) held short courses January 4-6, in Columbia, South Carolina. Instructors Dr. Paul Bliese and Dr. Rob Ployhart both from the University of South Carolina, together with Anne Smith of the University of Tennessee and Dr. Larry Williams, director of CARMA at the University of Nebraska-Lincoln, provided training on various methodologies aimed at skills development through lecture and lab-time.
Bliese taught Introduction to Multilevel Analysis, which provided students with the theoretical foundation and the resources and skills necessary to conduct a wide range of multilevel analyses. His course covered within-group agreement, nested two-level multilevel modeling and growth modeling. All practical exercises were conducted in R.
Ployhart covered Introduction to Longitudinal Analysis where he discussed theoretical and conceptual issues to be addressed when developing a longitudinal study. He covered how to design that study, including how to anticipate and reduce the problems that nearly always occur such as attrition. Concluding his course, there was considerable time spent reviewing and using different longitudinal analytic methods including repeated measure GLM< random coefficient growth models and latent growth models.
Smith’s course on Introduction to Text Analysis used hands-on text analysis exercises to introduce participants to text analysis. The course covered topics such as dictionary application, dictionary creation, template utilization and collocation analysis. The exploratory approach included an in vivo, manual coding exercise and a demonstration of coding techniques using computer aided qualitative data analysis software.
Finally, Williams taught Intermediate SEM, Model Evaluation. Students were expected to already have an introductory understanding of structural equation methods but were instructed on how to interpret and report results from SEM analyses, and how to conduct model comparisons to obtain information relevant to inferences about their models, as well as advantages and disadvantages of different approaches to model evaluation. The five sections, each with a lecture and lab, included review of model specification and parameter estimation, overview of model evaluation, logic and computations for goodness-of-fit measures, analysis of residuals and latent variable and model comparison strategies.
To review future CARMA short course offerings later this year in Adelaide, Detroit and Boston, visit: http://business.unl.edu/outreach/carma/short-courses/.