Meta-Analysis Resources

Tools for Those Who Summarize the Evidence Base

Resources and networking for those who conduct or interpret meta-analyses related to any phenomenon that is gauged in multiple studies.


Hi Guys, I have a nagging question. How do I compute Standardized Mean difference  (SMD)  (or the effect size or Cohen's d with Confidence Intervals included) from studies that only report between group difference and confidence intervals, without any data
for change, (mean +/-SD) from baseline. Given the change in (mean and
SD) from baseline, I know meta-analyst softwares can generate either SMD of MD
depending on which metric u chose on the software.

Summary of my question:

Given only the "between group differences" and baseline (mean+/-SD) for both groups, how can I generate SMD  in other to run my analysis or how do I feed
the between group difference into the software when what I am actually
interested in is the SMD? is there any way of back calculating the change (mean+/-SD) from baseline using the MD and confidence intervals between the two groups?

Thanks

Views: 1558

Replies to This Discussion

Gbeinerg,  I believe that the software package Comprehensive Meta-Analysis (www.meta-analysis.com) allows you to imput data in multiple formats.  As an example, if you have 4 studies with arm-level data (change +/- SD from baseline for each arm) and 1 study with trial-level data (difference b/w groups & 95% CI), the program will allow you to enter in this different data (you may have to change the confidence interval to a SD, I'm not 100% sure on that).  You can then run the analysis using either mean difference or standardized mean difference, depending on your preference.

 

As for back calculating the arm data, the best way I know of is to just contact the authors and ask for it.  I'd be interested in others thoughts as well.

 

Bill

RSS

© 2022   Created by Blair T. Johnson.   Powered by

Badges  |  Report an Issue  |  Terms of Service