| dc.description.abstract | Intrinsically nonlinear models are used rarely in psychology and social science research, despite being well suited for informing theory, directly testing key hypotheses, and identifying intraindividual variation in important psychological processes. Additionally, assessing the presence of moderation is often of key importance for psychological theory testing. However, methods for testing, plotting, and probing moderation were developed for linear models, and currently, their use remains largely restricted to linear models. Psychology researchers seeking to implement nonlinear models with moderated parameters currently face a variety of conceptual and logistical challenges. Therefore, the overarching aims of this dissertation are to establish the utility of nonlinear models for social science, and to derive novel methodological and software tools that facilitate the creation and visualization of nonlinear models with moderated parameters. First, a review of the methodological and applied literature demonstrates the enhanced theoretical and substantive contributions that may be made through use of moderated nonlinear models. Second, guidelines for moderated nonlinear model selection, parameterization, and specification are introduced. Third, conceptual and mathematical extensions of the Johnson-Neyman technique – the state-of-the-art method for probing and visualizing moderation – are derived such that this technique can now be applied to moderated nonlinear models. Finally, a new Shiny app is introduced, which enables researchers to fit, evaluate, and visualize nonlinear models with moderated parameters in a code-free environment. Ideally, the methods and software presented in this dissertation will reduce many of the key conceptual and logistical barriers that social scientists currently face when implementing moderated nonlinear models, thereby increasing the use of such models across psychology and social science. | |
