Conference Object

Simulation-Based Power Analysis in (Generalized) Linear Mixed Models

Author(s) / Creator(s)

Kumle, Levi

Abstract / Description

The statistical power of a research design is closely linked to the reliability and replicability of empirical findings. Accounting for power while planning a study is therefore crucial and often a requirement for submissions in scientific journals. However, this can quickly become highly difficult in practice – especially for more complex, but very popular analysis procedures like linear mixed models (LMMs). In this workshop, we will briefly cover the basics of power analysis, linear mixed models, and why the combination of both requires a simulation-based approach. We will then focus on the R-package mixedpower and how to use it to estimate power in LMMs. The general aim of this workshop will be to help researchers build intuitions about simulation-based power analyses, and to empower them to set up highly powered research designs when they plan to use mixed-effect models to analyse the resultant data. A prerequisite for this workshop is a basic knowledge of R. Although we will briefly cover the basics of LMMs, familiarity with LMMs and the R-package lme4 is strongly recommended.

Persistent Identifier

Date of first publication

2023-08-30

Is part of

PTOS, 2023, online

Publisher

PsychArchives

Citation

  • Author(s) / Creator(s)
    Kumle, Levi
  • PsychArchives acquisition timestamp
    2023-08-30T14:23:58Z
  • Made available on
    2023-08-30T14:23:58Z
  • Date of first publication
    2023-08-30
  • Abstract / Description
    The statistical power of a research design is closely linked to the reliability and replicability of empirical findings. Accounting for power while planning a study is therefore crucial and often a requirement for submissions in scientific journals. However, this can quickly become highly difficult in practice – especially for more complex, but very popular analysis procedures like linear mixed models (LMMs). In this workshop, we will briefly cover the basics of power analysis, linear mixed models, and why the combination of both requires a simulation-based approach. We will then focus on the R-package mixedpower and how to use it to estimate power in LMMs. The general aim of this workshop will be to help researchers build intuitions about simulation-based power analyses, and to empower them to set up highly powered research designs when they plan to use mixed-effect models to analyse the resultant data. A prerequisite for this workshop is a basic knowledge of R. Although we will briefly cover the basics of LMMs, familiarity with LMMs and the R-package lme4 is strongly recommended.
    en
  • Publication status
    unknown
    en
  • Review status
    unknown
    en
  • External description on another website
    https://leibniz-psychology.org/practices-and-tools-of-open-science/simulation-based-power-analysis
  • Persistent Identifier
    https://hdl.handle.net/20.500.12034/8665
  • Persistent Identifier
    https://doi.org/10.23668/psycharchives.13172
  • Language of content
    eng
    en
  • Publisher
    PsychArchives
    en
  • Is part of
    PTOS, 2023, online
    en
  • Is related to
    https://leibniz-psychology.org/ptos/
  • Is related to
    https://hdl.handle.net/20.500.12034/9887
  • Dewey Decimal Classification number(s)
    150
  • Title
    Simulation-Based Power Analysis in (Generalized) Linear Mixed Models
    en
  • DRO type
    conferenceObject
    en
  • Visible tag(s)
    ZPID Conferences and Workshops