R help - May 2014 - Help conduction Egger's test

Hi, 

I am currently conducting a meta analyses and wish to carry out Egger?s test. I
was just wondering, does the weighted linear regression model proposed by Egger
et al correspond to the "weighted regression with multiplicative
dispersion? option in Metafor?

Many thanks

Sultan

Yes, the 'traditional' Egger test is a weighted regression of the effect
size estimates against their standard errors with weights s2/vi, where s2 is a
multiplicative dispersion parameter. This is what you will get with:

regtest(x, model="lm", predictor="sei")

where 'x' is an object returned by the rma() function from a
fixed/random-effects model.

An example:

### load BCG vaccine data
data(dat.bcg)

### calculate log relative risks and corresponding sampling variances
dat <- escalc(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg,
data=dat.bcg)

### random-effects model
res <- rma(yi, vi, data=dat)

### classical Egger test
regtest(res, model="lm", predictor="sei")

Best,
Wolfgang

--   
Wolfgang Viechtbauer, Ph.D., Statistician   
Department of Psychiatry and Psychology   
School for Mental Health and Neuroscience   
Faculty of Health, Medicine, and Life Sciences   
Maastricht University, P.O. Box 616 (VIJV1)   
6200 MD Maastricht, The Netherlands   
+31 (43) 388-4170 | 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 Sultan Malik
> Sent: Monday, May 12, 2014 20:03
> To: r-help at r-project.org
> Subject: [R] Help conduction Egger's test
> 
> Hi,
> 
> I am currently conducting a meta analyses and wish to carry out Egger's
> test. I was just wondering, does the weighted linear regression model
> proposed by Egger et al correspond to the "weighted regression with
> multiplicative dispersion" option in Metafor?
> 
> Many thanks
> 
> Sultan
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.

At 19:02 12/05/2014, Sultan Malik wrote:
>Hi,
>
>I am currently conducting a meta analyses and wish to carry out 
>Egger's test. I was just wondering, does the weighted linear 
>regression model proposed by Egger et al correspond to the "weighted 
>regression with multiplicative dispersion" option in Metafor?
Dear Sultan

One thing I would suggest is to also use the ranktest function. In my 
experience they can give different results. You also need to look at 
the funnel plot of course and bear in mind that none of these methods 
is very satisfactory unless you have quite a number of fairly 
homogenous studies to synthesise.
>Many thanks
>
>Sultan
Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html