Fixed effects and variance components estimation in three‐level meta‐analysis

By S. Konstantopoulos. Research Synthesis Methods, 2011

500 citations recorded by the source corpus.

Meta‐analytic methods have been widely applied to education, medicine, and the social sciences. Much of meta‐analytic data are hierarchically structured because effect size estimates are nested within studies, and in turn, studies can be nested within level‐3 units such as laboratories or investigators, and so forth. Thus, multilevel models are a natural framework for analyzing meta‐analytic data. This paper discusses the application of a Fisher scoring method in two‐level and three‐level meta‐analysis that takes into account random variation at the second and third levels. The usefulness of the model is demonstrated using data that provide information about school calendar types. sas proc mixed and hlm can be used to compute the estimates of fixed effects and variance components. Copyright © 2011 John Wiley & Sons, Ltd.

Subfields: Artificial Intelligence, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/279dcb70c56eb6d8115385893e19c4e96f78bd7e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

The malleability of spatial skills: a meta-analysis of training studies. (2013, methodology): “Methods for applying HLM theory and estimation techniques to meta-analysis have been developed over the last 25 years (Jackson, Riley, & White, 2011; Kalaian & Raudenbush, 1996; Konstantopoulos, 2010).”
Creativity and Academic Achievement: A Meta-Analysis (2017, methodology): “To analyze main effects, we used multilevel meta-analysis (Cheung, 2014, 2015; Konstantopoulos, 2011; Lebuda, Zabelina, & Karwowski, 2015), because individual correlations were clustered within studies.”
Retest effects in cognitive ability tests: A meta-analysis (2018, background): “…of administrations c (1.2, 1.3, or 1.4), yijc is the jth effect size from the ith study, μc is the true SMCR, uic is a random effect at the level of studies, wijc is a random effect at the level of samples, and εijc is the sampling error (e.g., Bryk & Raudenbush, 1988; Konstantopoulos, 2011).”
Nitrogen fertiliser replacement values for organic amendments appear to increase with N application rates (2017, background): “These models can account for random effects (Konstantopoulos 2011).”
Impacts of nitrogen addition on plant species richness and abundance: A global meta‐analysis (2018, methodology): “We nested the individ‐ ual estimates within the experiment grouping‐level in the random structure of the models to account for the possibility that the underlying true effects within experiments are not homogeneous (Konstantopoulos, 2011).”
How work engagement relates to performance and absenteeism: a meta-analysis (2021, result): “Furthermore, we also considered any data dependency arising from several studies by the same or similar groups of authors (Konstantopoulos, 2011).”
Effectiveness of Self-Compassion Related Therapies: a Systematic Review and Meta-analysis (2018, unknown): “To correct for these correlated comparisons (Higgins and Green 2011), we used a multilevel meta-analytic model (Konstantopoulos 2011; Weisz et al. 2013).”
Meta-Analysis of Present-Bias Estimation using Convex Time Budgets (2019, methodology): “As an alternative approach for handling statistically dependent PB estimates within each paper, we also apply a multi-level random-effects model (ML; Konstantopoulos, 2011; Van den Noortgate et al., 2013).17 Let PBij denote the jth estimate of the PB parameter from study i.”
Modeling dependent effect sizes with three-level meta-analyses: a structural equation modeling approach. (2014, methodology): “This article uses the three-level meta-analysis (e.g., Konstantopoulos, 2011; Van den Noortgate, López-López, Marín-Martínez, & SánchezMeca, 2012) to model unknown dependence.”
Creativity and Well‐being: A Meta‐analysis (2020, methodology): “To control for this dependency, researchers suggested adopting a multilevel approach (Cheung, 2014; Hox, 2002; Konstantopoulos, 2011; Scammacca, Roberts, & Stuebing, 2014; Stevens & Taylor, 2009; Van den Noortgate, L opez-L opez, Mar ın-Mart ınez, & S anchez-Meca, 2013).”
The effectiveness of celebrity endorsements: a meta-analysis (2016, methodology): “This analysis is necessary for testing whether it makes sense to analyze different types of effect sizes separately (between-type of effect size variability) and whether it makes sense to analyze our moderators at all (between-study variability; Konstantopoulos 2011).”
Methods for dealing with multiple outcomes in meta-analysis: a comparison between averaging effect sizes, robust variance estimation and multilevel meta-analysis (2017, methodology): “Also when there are multiple outcomes in a study, a multilevel meta-analysis can be used (Cheung, 2014; Konstantopoulos, 2011; Van den Noortgate et al., 2013, 2015).”
Handling Complex Meta-analytic Data Structures Using Robust Variance Estimates: a Tutorial in R (2016, unknown): “(Konstantopoulos, 2011; Raudenbush & Bryk, 2002).”
Robust variance estimation with dependent effect sizes: practical considerations including a software tutorial in Stata and spss (2014, methodology): “When all of the dependencies are of this type, the meta-regression model can be estimated using software such as HLM (Scientific Software International, Inc., Skokie, IL, USA) (Konstantopoulos, 2011; Raudenbush and Bryk, 2002).”