Communication Methods and Measures, 11, 1-30 This paper is supported in part by work that appears in Amanda's MA thesis, which you can download here. A tutorial on testing, visualizing, and probing interaction involving a multicategorical variable in linear regression analysis. Australasian Marketing Journal, 25, 76-81 The analysis of mechanisms and their contingencies: PROCESS versus structural equation modeling. Regression analysis and linear models: Concepts, applications, and implementation. Behaviour Research and Therapy, 98, 39-57. Regression-based statistical mediation and moderation analysis in clinical research: Observations, recommendations, and implementation. Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (2nd Edition). Partial, conditional, and moderated moderated mediation: Quantification, inference, and interpretation. Easy statistical mediation analysis with distinguishable dyadic data. Cambridge University Press.Ĭoutts, J., Hayes, A. Hallquist (Eds.) Handbook of research methods in clinical psychology. Mediation, moderation, and conditional process analysis: Regression-based approaches for clinical research. American Behavioral Scientist, 64, 19-54. ![]() Conditional process analysis: Concepts, computation, and advances in the modeling of the contingencies of mechanisms. Communication Methods and Measures, 14, 1-24. Use omega rather than Cronbach's alpha for quantifying reliability. Multilevel modeling methods with introductory and advanced applications. Bookmark this page and check back often for latest developments and publications. We also offer short courses and workshops as part of outreach, and over time we anticipate building an archive of white papers housed here that offer applied guidance to researchers. Indeed, such questions often inform us of holes in the literature and needs that exist that we may not be aware of. ![]() Outreach is an important component of this lab, and we are always happy to offer advice through email to people grappling with the implementation of methods described in our work. We focus on data analysis problems substantive researchers encounter while offering statistical tools (usually in the form of macros or code) that make them easy to put into practice with software that most researchers are already familiar with, without requiring the expertise, guidance, or knowledge of a statistician or computer scientist.Īlthough the traditional peer reviewed journal article is and will always be an important means of disseminating the work of the MAC lab, length restrictions imposed by most journals often reduce how much detail and practical training can be provided through this medium. Members of the lab recognize that new methods take hold in a discipline when they are implemented in software that is widely used and are communicated to researchers in language that doesn't require advanced training in mathematics or statistics. For this reason, our work and writing is guided by the needs of the final user in mind rather than the expert methodologist. Most substantive researchers are too busy doing the work of the business to dedicate important resources to keeping up with all the nuances in methodology, statistical programming, and the like. As a result, research in this area has exploded, and new methods are becoming increasingly sophisticated and precise but sometimes require a level of mathematical background to understand them or programming skills to implement them that many substantive researchers do not have. Mediation and moderation analysis have become staples of the curriculum in the graduate programs of disciplines that rely on social science methodologies. Thus, the MAC lab focuses its work on developing, evaluating, and disseminating research and practical statistical methods and tools useful for understanding the processes by which causal effects operate (mediation) and the circumstances, contexts, or individual differences that influence the magnitude of those effects (moderation). That is, deeper understanding of a phenomenon is enhanced by quantification of and inference about the process or processes underlying a causal effect and its contingencies. The work of the Mechanisms and Contingencies (MAC) Lab is guided by the principle that causal effects are best understood by establishing how those effects operate and the circumstances that facilitate or hinder them.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |