This is to clarify a point in my Stata Journal article on contour enhanced funnel plots for meta-analysis (latest edition, pages 242-254).
I commented that when the metatrim command was run on the magnesium therapy meta-analysis that no studies were filled (page 251). However, in this example it was of interest to investigate whether studies with positive outcomes were missing. I used metatrim with its default options but this situation requires the use of metatrim's -flip- option (available in version 1.0.5). When metatrim was applied with the -flip- option to the magnesium therapy meta-analysis between 6 and 8 studies were filled depending on the options used.
Thanks to Tom Steichen for spotting this.
Best regards,
Tom Palmer
PhD student,
Dept. Health Sciences,
University of Leicester
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
