Browse/search for people

Publication - Dr Jose Lopez-Lopez

    Testing Categorical Moderators in Mixed-Effects Meta-analysis in Presence of Heteroscedasticity

    Citation

    Rubio-Aparicio, M, Lopez-Lopez, JA, Viechtbauer, W, Marín-Martínez, F, Botella, J & Sánchez-Meca, J, 2019, ‘Testing Categorical Moderators in Mixed-Effects Meta-analysis in Presence of Heteroscedasticity’. Journal of Experimental Education.

    Abstract

    Mixed-effects models can be used to examine the association between a categorical moderator and the magnitude of the effect size. Two approaches are available to estimate the residual between-studies variance, τ_res^2, namely separate estimation within each category of the moderator versus pooled estimation across all categories. We examine, by means of a Monte Carlo simulation study, both approaches for τ_res^2 estimation in combination with two methods to test the statistical significance of the moderator, namely the Wald-type χ^2 and F tests. Results suggest that the F test using a pooled estimate of τ_res^2 across categories is the best option in most conditions, although the F test using separate estimates of τ_res^2 is preferable if the residual heterogeneity variances are heteroscedastic.

    Full details in the University publications repository