Fig 1.
Ordered differences between effect estimates on Fisher-z scale for all included study-pairs (n = 87) in both replication projects with their 95% confidence interval.
The dashed horizontal line indicates no difference in effect size.
Fig 2.
Left: The distribution of the observed standardized difference of the original-replication-study-pair (n = 87) compared to the standard normal distribution.
Right: The p-values from the Q-test for heterogeneity within original-replication study-pairs, as well as the p-value for the overall test for heterogeneity between all study-pairs, included in both replication projects.
Table 1.
Summary of investigated location meta-regression models with multiplicative and additive heterogeneity. The location coefficient estimates are shown with their 95% confidence intervals (95%CI) and the residual heterogeneity. The first model is the weighted unadjuted meta-regression model relating the difference in effect size to a constant, as in Eqs 3 and 4. For the second model, one covariate was added into the meta-regression as a proof-of-concept. The third model represents the final model selected via the model selection procedure. Additional information on the covariates is added in the note below the table.
Fig 3.
The AIC for the multiplicative and the additive models with best performance (min AIC) for each possible number of covariates included.
The residual multiplicative heterogeneity parameter and additive heterogeneity variance
of the respective models are also shown. At least one covariate, namely the original standard error, is included. The minimum AIC value is highlighted.
Table 2.
The ten best multiplicative location-scale models according to their AIC and depending on the selection of location and scale covariates. The location and scale covariates are marked with a check-mark if they are present in the model and with a dash if they are not. The last row of the Table shows the AIC of each model.
Table 3.
The ten best additive location-scale models according to their AIC and depending on the selection of location and scale covariates. The location and scale covariates are marked with a check-mark if they are present in the model and with a dash if they are not. The last row of the Table shows the AIC of the specific model.
Table 4.
The final multiplicative and additive location-scale meta-regression models minimising the AIC. The location and scale coefficient estimates are shown together with their 95% confidence intervals (95%CI). Only a subset of the covariates used for the location are kept to explain the scale. Additional information on the covariates is added in the note below the table.