bayesmeta (version 3.4)

forestplot.escalc: Generate a forest plot for an escalc object (based on the forestplot package's plotting functions).

Description

Generates a forest plot, showing estimates along with their 95 percent confidence intervals.

Usage

# S3 method for escalc
forestplot(x, labeltext, exponentiate=FALSE,
           digits=2, plot=TRUE,
           fn.ci_norm, fn.ci_sum, col, boxsize, ...)

Arguments

x

an escalc object.

labeltext

an (alternative) “labeltext” argument which is then handed on to the forestplot() function (see the help there). You can use this to change contents or add columns to the displayed table; see the example below.

exponentiate

a logical flag indicating whether to exponentiate numbers (effect sizes) in table and plot.

digits

The number of significant digits to be shown. This is interpreted relative to the standard errors of all estimates.

plot

a logical flag indicating whether to actually generate a plot.

fn.ci_norm, fn.ci_sum, col, boxsize, ...

other arguments passed on to the forestplot package's forestplot function (see also the help there).

Author

Christian Roever

Details

Generates a forest plot illustrating the data returned by the “escalc()” function (showing the estimates potentially to be meta-analyzed, but without a combined summary estimate).

References

C. Roever. Bayesian random-effects meta-analysis using the bayesmeta R package. Journal of Statistical Software, 93(6):1-51, 2020. tools:::Rd_expr_doi("10.18637/jss.v093.i06").

C. Lewis and M. Clarke. Forest plots: trying to see the wood and the trees. BMJ, 322:1479, 2001. tools:::Rd_expr_doi("10.1136/bmj.322.7300.1479").

R.D. Riley, J.P. Higgins and J.J. Deeks. Interpretation of random effects meta-analyses. BMJ, 342:d549, 2011. tools:::Rd_expr_doi("10.1136/bmj.d549").

See Also

escalc, forestplot, forestplot.bayesmeta, forestplot.bmr.

Examples

# load data:
data("CrinsEtAl2014")

# compute effect sizes (log odds ratios) from count data
# (using "metafor" package's "escalc()" function):
crins.es <- escalc(measure="OR",
                   ai=exp.AR.events,  n1i=exp.total,
                   ci=cont.AR.events, n2i=cont.total,
                   slab=publication, data=CrinsEtAl2014)
print(crins.es)

########################
# generate forest plots;
# with default settings:
forestplot(crins.es)

# exponentiate values (shown in table and plot), show vertical line at OR=1:
forestplot(crins.es, expo=TRUE, zero=1)

# logarithmic x-axis:
forestplot(crins.es, expo=TRUE, xlog=TRUE)

# show more decimal places:
forestplot(crins.es, digits=3)

# change table values:
# (here: add columns for event counts)
fp <- forestplot(crins.es, expo=TRUE, plot=FALSE)
labtext <- fp$labeltext
labtext <- cbind(labtext[,1],
                 c("treatment",
                   paste0(CrinsEtAl2014[,"exp.AR.events"], "/", CrinsEtAl2014[,"exp.total"])),
                 c("control",
                   paste0(CrinsEtAl2014[,"cont.AR.events"], "/", CrinsEtAl2014[,"cont.total"])),
                 labtext[,2:3])
labtext[1,4] <- "OR"
print(fp$labeltext) # before
print(labtext)      # after
forestplot(crins.es, labeltext=labtext, expo=TRUE, xlog=TRUE)

# see also the "forestplot" help for more arguments that you may change,
# e.g. the "clip", "xticks", "xlab" and "title" arguments,
# or the "txt_gp" argument for label sizes etc.:
forestplot(crins.es, clip=c(-4,1), xticks=(-3):0,
           xlab="log-OR", title="pediatric transplantation example",
           txt_gp = fpTxtGp(ticks = gpar(cex=1), xlab = gpar(cex=1)))


###########################################################
# In case effects and standard errors are computed already
# (and normally one wouldn't need to call "escalc()")
# you can still use "escalc()" to assemble the plot, e.g.:

data("HinksEtAl2010")
print(HinksEtAl2010)

hinks.es <- escalc(yi=log.or, sei=log.or.se,
                   slab=study, measure="OR",
                   data=HinksEtAl2010)

forestplot(hinks.es)