[R] Comparing pooled proportions(complication and reoperation rates) of different treatment modalities

Jay Zola jayjay.1988 at hotmail.nl
Fri Jun 23 21:59:51 CEST 2017

Dear sir/madame,

Currently I am writing a meta analysis on complications and reoperations of 5 treatment modalities after an extra-articular distal radius fracture. The treatment modalities are EF, IMN, KW, VPO and PC as the golden standard. We have included 22 studies, 10 RCTs and 12 prospective studies. All examining different treatment methods. We retrieved the data out of these studies and pooled the complication and reoperation rates(n/N). Now we want to compare the pooled proportion of each treatment modality to the golden standard of PC(plaster casting). So I want to do 4 separate comparisons using the chi squared method. I looked it up online and at the meta package guide(meta is the package I used), but wasn't able to find useful information. I first posted my question onto the stats.stackexchange website but was redirected to the mailing list of r-help. I have added a picture of the most important parts of the code (not the egger's regression, funnel, trim and fill and outcome.pdf parts of it because it didn't fit). I have added the data in excel and spss file to my dropbox, and added the complete Rcode to a Word file in my dropbox as well. The links below will refer you to them as preferred by the posting guide. Hopefully someone can help me.

Thank you very much.

Excel datafile: https://www.dropbox.com/s/19402gt0x1agt9f/Excel%20file%20Distal%20Radius%20Fracture%20basic.xlsx?dl=0

Excel file Distal Radius Fracture basic.xlsx<https://www.dropbox.com/s/19402gt0x1agt9f/Excel%20file%20Distal%20Radius%20Fracture%20basic.xlsx?dl=0>
Shared with Dropbox

SPSS datafile: https://www.dropbox.com/s/h81pphxkfk74hzo/Meta-Analyse%20Complications%20and%20Reoperations.sav?dl=0


Meta-Analyse Complications and Reoperations.sav<https://www.dropbox.com/s/h81pphxkfk74hzo/Meta-Analyse%20Complications%20and%20Reoperations.sav?dl=0>
Shared with Dropbox

Rcode file Word: https://www.dropbox.com/s/67pnfpi10qu110v/R%20code%20voor%20forrest%20en%20funnel%20plots.rtf?dl=0


R code voor forrest en funnel plots.rtf<https://www.dropbox.com/s/67pnfpi10qu110v/R%20code%20voor%20forrest%20en%20funnel%20plots.rtf?dl=0>
Shared with Dropbox



Comparing pooled propotions using R for a meta-analysis<https://stats.stackexchange.com/questions/286920/comparing-pooled-propotions-using-r-for-a-meta-analysis>
For a meta-analysis I have pooled single proportions(complication rates) of several treatment methods. Now I would like to compare them(the 4 treatment modalities separately with the golden standar...

Van: David Winsemius <dwinsemius at comcast.net>
Verzonden: vrijdag 23 juni 2017 20:18
Aan: Jay Zola
CC: r-help at r-project.org
Onderwerp: Re: [R] Comparing pooled proportions(complication and reoperation rates) of different treatment modalities

> On Jun 23, 2017, at 5:53 AM, Jay Zola <jayjay.1988 at hotmail.nl> wrote:
> Dear sir/madame,
> I am currently writing a meta-analysis on the complication and reoperation rates of 5 different treatment modalities after a distal radius fracture. I was able to pool the rates of the 5 different rates using R. Now I have to compare the pooled rates of the 4 treatment modalities with the golden standard separately. I though the chi squared test would be the best method. How do I do that using r. The R code I have used for the former calculation are added as a Word-file attachment.

Not an acceptable format to the listserv program. Policy is set by the host institution. Use plain text.

> Your help would be highly appreciated.
> Yours sincerely,
> Student
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help

The main R mailing list, for announcements about the development of R and the availability of new code, questions and answers about problems and solutions using R ...

> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius
Alameda, CA, USA

	[[alternative HTML version deleted]]

More information about the R-help mailing list