A Tutorial on Tailored Simulation-Based Power Analysis for Experimental Designs with Generalized Linear Mixed Models
- When planning experimental research, determining an appropriate sample size and using suitable statistical models are crucial for robust and informative results. However, the recent replication crisis underlines the need for more rigorous statistical methodology and well-powered designs. Generalized linear mixed models (GLMMs) offer a flexible statistical framework to analyze experimental data with complex (e.g., dependent and hierarchical) data structures. Yet, available methods and software for a priori power analyses for GLMMs are often limited to specific designs, while data simulation approaches offer more flexibility. Based on a practical case study, the current tutorial equips researchers with a step-by-step guide and corresponding code for conducting tailored a priori power analyses to determine appropriate sample sizes with GLMMs. Finally, we give an outlook on the increasing importance of simulation-based power analysis in experimental research.
Verfasserangaben: | Timo KochORCiD, Florian PargentORCiD, Anne-Kathrin KleineORCiD, Eva LermerORCiD, Susanne GaubeORCiD |
---|---|
DOI: | https://doi.org/10.31234/osf.io/rpjem |
Titel des übergeordneten Werkes (Englisch): | PsyArXiv Preprints |
Dokumentart: | Preprint |
Sprache: | Englisch |
Datum der Veröffentlichung (online): | 18.09.2023 |
Jahr der Erstveröffentlichung: | 2023 |
Datum der Freischaltung: | 22.12.2023 |
Freies Schlagwort / Tag: | data simulation; generalized linear mixed model; power analysis; sample size |
Seitenzahl: | 39 |
Open Access: | ja (Diamant) |
Fakultät: | Fakultät für angewandte Geistes- und Naturwissenschaften |
DDC-Klassifikation: | 3 Sozialwissenschaften / 30 Sozialwissenschaften, Soziologie |
Institute und Forschungsgruppen: | HSA_april: Forschungsgruppe für angewandte Wirtschaftspsychologie (Applied Psychology for Research and Innovation Lab) |
Lizenz (Deutsch): | ![]() |
Frontdoor-URL: | https://opus4.kobv.de/opus4-hs-augsburg/1472 |