Quantitative Methods for Meta-analysis

This workshop provides a hands-on introduction to the quantitative methods used in meta-analytic studies. This workshop is designed for researchers in the social, behavioral, and medical sciences who want to develop the skills to effectively apply meta-analytic quantitative methods to their own data.

Instructors:
Colin E. Vize, PhD (University of Pittsburgh)

Workshop Dates and Times:
Thursday, August 15th, 2024, 9:30am to 4:30pm ET
Friday, August 16th, 2024, 9:30am to 4:30pm ET

Workshop Format:
Two-Day Synchronous Online Workshop

Meta-analysis is an extremely valuable research tool, and is used across a wide range of scientific disciplines, including the social and behavioral sciences. Moreover, meta-analytic studies typically enjoy a privileged position in terms of the strength of evidence they can provide, relative to single studies.

However, meta-analytic methods have become quite sophisticated, and researchers may feel intimidated or not know where to start when it comes to analyzing their own meta-analytic data. Meta-analyses also present the researcher with a wide range of decisions to be made at each stage of the project.

This two-day workshop is designed as a gentle introduction to the fundamental quantitative methods used in meta-analyses. The workshop aims to provide a solid conceptual knowledge of effect sizes, common meta-analytic models (e.g., fixed-effect and random-effects models), tests of effect size heterogeneity, meta-regression, and handling dependencies among effect sizes with multilevel meta-analysis. The workshop will also focus on how to appropriately apply these methods to real data using worked examples.

The workshop assumes that attendees have no prior experience independently conducting a meta-analysis. Some prior experience with R and RStudio is helpful, as all examples will be presented using the freely available ‘metafor’ package in R. Prior knowledge of R and RStudio can be limited to setting a working directory, loading data, and running provided R code.

What you’ll learn

  • Common Models for Meta-analytic data - Fixed-effect models, random-effects models, similarities and differences between these models

  • Effect Sizes - Different kinds of effect sizes that can be examined, effect size corrections for different measurement artifacts (e.g., measurement error)

  • Effect Size Heterogeneity and Meta-regression - Understanding and testing for heterogeneity among effect sizes, explaining effect size heterogeneity with meta-regression

  • Multi-level Meta-analysis - Understanding dependency among effect sizes, different strategies for handling dependency among effect sizes, 2- and 3-level meta-analysis

  • Using R to Conduct Meta-analysis - Develop familiarity with the ‘metafor’ package in R, convert between effect sizes in R, run fixed-effect and random-effects models, plotting meta-analytic results.

Registration Options

Quantitative Methods for Meta-Analysis

  • Professional
  • $599
  • Baseline Price for Faculty,
    Staff, and Other Professionals
  • Click Register Below
  • Trainee
  • $599 $399
  • 33% Discount for
    Students and Postdocs
  • Use code "TRAINEE" at Checkout

 FAQs

  • This workshop was purposefully designed for researchers in the social, behavioral, and medical sciences who are wanting to learn more about meta-analysis but may not have received much (if any) formal training in meta-analytic methods. The workshop is designed to be accessible to learners with even limited formal quantitative training (e.g., first-year graduate students). Portions of the workshop focused on multilevel meta-analysis does not require previous experience with multilevel modeling, though familiarity with nested data structures will be helpful (but not assumed). This workshop is introductory and appropriate for faculty, staff, and students at both the graduate and advanced undergraduate levels.

    *PLEASE NOTE* This workshop will not focus on the early planning stages of a meta-analysis. While developing search terms, conducting a literature search, and coding study information are critical parts of a meta-analysis project, the workshop will focus on how to appropriately analyze meta-analytic data after it has been collected.

  • This workshop is for learners wanting to learn how to conduct the core analyses of a meta-analysis (e.g., compute a weighted effect size, examine effect size heterogeneity). Familiarity with multiple regression and nested data structures may be helpful but will not be assumed.

  • This workshop assumes that attendees have no prior experience independently conducting a meta-analysis.

    It does, however, assume that learners have basic computing skills such as the ability to download and manage (e.g., copy and paste) files, install and run software, and use a web browser to access workshop materials. Moreover, the workshop does assume some familiarity with R and RStudio, such as being able to set a working directory, load data, and run provided R code.

  • R and RStudio; 'metafor' package in R

  • Registered learners will gain access to the Zoom link and passcode to attend the synchronous workshop, as well as video recordings of the lectures, downloadable slideshows, and all data and R code used during the workshop.