Appearance of Forest Plot

Hi,

Can you give a reproducible example of what you did?  My intuition is
that you could do it using par(), but I am not sure what package
metabin() is from (certainly none of the ones that load by default),
and I have even less idea how you created a forest plot (there are
many ways in R).  If you make up a little dataset (or use one of the
built in ones) and then show your code using that example, we can
replicate what you did and provide help.

I would also say that for faceting or otherwise breaking up your data
but having on graph, I find either the lattice or ggplot2 packages
easier to work with than base graphics.

Cheers,

Josh

====================

and provide commented, minimal, self-contained, *reproducible code*.

====================

Hi All,

I have conducted a meta analysis using the metabin function. I want to plot
5 subgroups on the same forest plot. I have managed to do this using the
byvar argument but when i plot the forest plot in R graphics I am unable to
view the very top and very bottom of the image. It is as though the plot is
too long. Is there a way in which I can ask R to show the entire plot within
the boundaries of the window?

Many Thanks.
--
View this message in context: http://r.789695.n4.nabble.com/Appearance-of-Forest-Plot-tp3075326p3075326.html
Sent from the R help mailing list archive at Nabble.com.

______________________________________________
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.

Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/

Hi Josh,

Thank you for your response. I have recreated my issue using the Olkin 95
data and subgrouping by year of study - I hope it shows where my problem
lies:


library(meta)

data(Olkin95)

metaeg<-metabin(event.e, n.e, event.c, n.c, studlab = author,
data=Olkin95, method="MH",
sm="OR", MH.exact=FALSE, RR.cochrane=FALSE, comb.fixed=TRUE,
comb.random=TRUE,
title="", complab="", outclab="",
label.e="Active", label.c="Control",
print.CMH=FALSE, warn=FALSE)

Olkin95$year<-Olkin95$year
metaeg$year<-addvar(metaeg,Olkin95,"year",by.y="author")
as.data.frame(metaeg)

print.meta(metaeg)
forest (metaeg,byvar=year)

Any ideas would be very much appreciated. Thanks again!

View this message in context: http://r.789695.n4.nabble.com/Appearance-of-Forest-Plot-tp3075326p3076271.html
Sent from the R help mailing list archive at Nabble.com.

Hi,

Thanks for the example!  What about plotting it to pdf (or you can use
your favorite file format, just switch png(), jpeg(), bmp(), tiff()
for the pdf() call)?

pdf(file = "temp.pdf", width = 14, height = 38)
forest (metaeg,byvar=year)
dev.off()

I attached the PDF result so you could look at it.  As far as I can
tell, forest() does not mess with the par() settings too much, but
slightly resizing things/fiddling with margins did not give me nearly
what I would need to fit something that big on a screen.  From a PDF
or some graphics format though, it is easy to zoom in or out until the
image fits.  An alternative might be to break up the one big plot into
2-3 smaller ones.

Cheers,

Josh

Hi Josh,

Thank you for your response. I have recreated my issue using the Olkin 95
data and subgrouping by year of study - I hope it shows where my problem
lies:


library(meta)

data(Olkin95)

metaeg<-metabin(event.e, n.e, event.c, n.c, studlab = author,
data=Olkin95, method="MH",
sm="OR", MH.exact=FALSE, RR.cochrane=FALSE, comb.fixed=TRUE,
comb.random=TRUE,
title="", complab="", outclab="",
label.e="Active", label.c="Control",
print.CMH=FALSE, warn=FALSE)

Olkin95$year<-Olkin95$year
metaeg$year<-addvar(metaeg,Olkin95,"year",by.y="author")
as.data.frame(metaeg)

print.meta(metaeg)
forest (metaeg,byvar=year)

Any ideas would be very much appreciated. Thanks again!
--
View this message in context: http://r.789695.n4.nabble.com/Appearance-of-Forest-Plot-tp3075326p3076271.html
Sent from the R help mailing list archive at Nabble.com.

______________________________________________
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.

--
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: temp.pdf
Type: application/pdf
Size: 112337 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20101207/6a56df76/attachment.pdf>