Hi,
I would like to find out what the pooled Standard Error of a meta-analysis effect size estimate is opposed to the pooled 95% Confidence Intervals.
The dataset for the meta-analysis contains 54 different study results.
As studies reported a combination of mean and SD scores, 2x2 table data or proportions, I used the meta eff command (in STATA 17) to transform the data in each individual study to a common effect size metric (using methods described in the Cochrane handbook of systematic reviews). This gives the SMD effect sizes and their standard errors for each of the 54 studies in the dataset.
Once I transformed the data to a common effect size metric (with SE) for each individual study, I then used the metan command to get the overall effect size estimate.
The command I used is: metan eff SEeff, label (namevar=Author) random lcols (Author samplesize).
So I have the DerSimonian-Laird Random Effects Meta-Analysis results with the metan command.
The STATA outputs for this display the individual studies SMD effect size estimates and their associated 95% Confidence Intervals as well as the pooled SMD effect size estimate and the associated 95% Confidence Intervals.
I need Standard Error of the effect size.
Is there a way I can display the pooled Standard Error of the effect size opposed to the 95% Confidence Intervals?
Any clarification you can provide would be much appreciated.
Kinds regards
Nora
I would like to find out what the pooled Standard Error of a meta-analysis effect size estimate is opposed to the pooled 95% Confidence Intervals.
The dataset for the meta-analysis contains 54 different study results.
As studies reported a combination of mean and SD scores, 2x2 table data or proportions, I used the meta eff command (in STATA 17) to transform the data in each individual study to a common effect size metric (using methods described in the Cochrane handbook of systematic reviews). This gives the SMD effect sizes and their standard errors for each of the 54 studies in the dataset.
Once I transformed the data to a common effect size metric (with SE) for each individual study, I then used the metan command to get the overall effect size estimate.
The command I used is: metan eff SEeff, label (namevar=Author) random lcols (Author samplesize).
So I have the DerSimonian-Laird Random Effects Meta-Analysis results with the metan command.
The STATA outputs for this display the individual studies SMD effect size estimates and their associated 95% Confidence Intervals as well as the pooled SMD effect size estimate and the associated 95% Confidence Intervals.
I need Standard Error of the effect size.
Is there a way I can display the pooled Standard Error of the effect size opposed to the 95% Confidence Intervals?
Any clarification you can provide would be much appreciated.
Kinds regards
Nora
Comment