Skip to content

Metafor package

2 messages · Prof. Mario Petretta, Viechtbauer Wolfgang (STAT)

#
I have some question about metafor package.

I'm interest to perform a random effect meta-analysis of proportion  
(single group summary of prevalence of disease in a population as  
reported by different study)
It ask:
1. "PFT":  The Freeman-Tukey double arcsine transformed proportion is  
reported to be equal to 1/2*(asin(sqrt(xi/(ni+1))) +  
asin(sqrt((xi+1)/(ni+1)))). Hovewer, i also found the same formula but  
without 1/2*.

2. how "vi", the corresponding (estimated) sampling variance is  
calculated? (i.e. the formula used to estimate "vi")

3. it is possible to return a forest plot with the backtransformed  
value of proportion, confidenc interval and weight and not with the  
transformed value after performing rma.uni?

Many thanks

Mario Petretta
Dipartimento di Medicina Clinica Scienze Cardiovascolari e Immunologiche
Facolt? di Medicina e Chirurgia
Universit? di Napoli Federico II
081 - 7462233
#
Dear Mario,

1) Whether to use 1/2* or not is arbitary. It's just a multiplicative constant.

2) vi <- 1/(4*ni + 2)

If one leave off the 1/2* part, then it would be vi <- 1/(ni + 1/2).

3) Yes, but it takes a bit more work. Fortunately, the same issue was raised not very long ago, so the following post should essentially answer your question:

https://stat.ethz.ch/pipermail/r-help/2010-December/263286.html

Best,

--
Wolfgang Viechtbauer
Department of Psychiatry and Neuropsychology
School for Mental Health and Neuroscience
Maastricht University, P.O. Box 616
6200 MD Maastricht, The Netherlands
Tel: +31 (43) 368-5248
Fax: +31 (43) 368-8689
Web: http://www.wvbauer.com


----Original Message----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On
Behalf Of petretta at unina.it Sent: Monday, December 20, 2010 13:26
To: r-help at r-project.org
Subject: [R] Metafor package