settings.meta: Print and change default meta-analysis settings in R package...

In meta: General Package for Meta-Analysis

Print and change default meta-analysis settings in R package meta

Description

Print and change default settings to conduct and print or plot meta-analyses in R package meta. The following general settings are available: Review Manager 5, Journal of the American Medical Association.

Usage

settings.meta(..., quietly = TRUE)

Arguments

...	Arguments to change default settings.
quietly	A logical indicating whether information on settings should be printed.

Details

This function can be used to define defaults for several arguments (i.e., assignments using gs) of the following R functions: metabin, metacont, metacor, metacr, metagen, metainc, metaprop, metarate

Furthermore, some of these settings are considered to print meta-analysis results and to produce forest plots.

The function can be used to either change individual settings (see Examples) or use one of the following general settings:

• settings.meta("RevMan5")

• settings.meta("BMJ")

• settings.meta("JAMA")

• settings.meta("IQWiG5")

• settings.meta("IQWiG6")

• settings.meta("geneexpr")

• settings.meta("meta4")

• settings.meta("meta7")

The first command can be used to reproduce meta-analyses from Cochrane reviews conducted with Review Manager 5 (RevMan 5) and specifies to use a RevMan 5 layout in forest plots.

The second command can be used to generate forest plots in BMJ layout.

The third command can be used to generate forest plots following instructions for authors of the Journal of the American Medical Association (https://jamanetwork.com/journals/jama/pages/instructions-for-authors/). Study labels according to JAMA guidelines can be generated using labels.meta.

The next commands implement the recommendations of the Institute for Quality and Efficiency in Health Care, Germany (IQWiG) accordinging to General Methods 5 and 6, respectively (https://www.iqwig.de/en/about-us/methods/methods-paper/).

The setting "geneexpr" can be used to print p-values in scientific notation and to suppress the calculation of confidence intervals for the between-study variance.

The last settings use the default settings of R package meta, version 4 and 7.0-0, respectively, or below.

RevMan 5 settings, in detail:

Argument	Value	Comment
method.random.ci	"classic"	only available method in RevMan 5
method.tau	"DL"	only available method in RevMan 5
method.I2	"Q"	only available method in RevMan 5
tau.common	FALSE	common between-study variance in subgroups
MH.exact	FALSE	exact Mantel-Haenszel method
RR.Cochrane	TRUE	calculation of risk ratios
Q.Cochrane	TRUE	calculation of heterogeneity statistic
exact.smd	FALSE	exact formulae for Hedges' g and Cohen's d
layout	"RevMan5"	layout for forest plots
prediction	FALSE	no prediction interval
test.overall	TRUE	print information on test of overall effect
test.subgroup	TRUE	print information on test for subgroup differences
test.effect.subgroup	TRUE	print information on test for effect in subgroups
forest.I2	TRUE	show heterogeneity statistic I2 in forest plots
forest.tau2	TRUE	show between-study heterogeneity
		variance in forest plots
forest.tau	FALSE	do not show between-study heterogeneity
		standard deviation in forest plots
forest.Q	TRUE	show heterogeneity statistic Q in forest plots
forest.pval.Q	TRUE	show p-value of test for heterogeneity in forest plots
forest.Rb	FALSE	do not show heterogeneity statistic Rb in forest plots
digits.tau2	3	number of digits for tau-squared
digits.tau	4	number of digits for square root of tau-squared
digits.I2	0	number of digits for I-squared measure
CIbracket,	"["
CIseparator	", "	print confidence intervals as "[., .]"
header.line,	TRUE	print header line

BMJ settings:

Argument	Value	Comment
layout	"BMJ"	layout for forest plots
test.overall	TRUE	print information on test of overall effect
test.subgroup	FALSE	print information on test for subgroup differences
test.effect.subgroup	FALSE	print information on test for effect in subgroups
forest.I2	TRUE	show heterogeneity statistic I2 in forest plots
forest.tau2	TRUE	show between-study heterogeneity
		variance in forest plots
forest.tau	FALSE	do not show between-study heterogeneity
		standard deviation in forest plots
forest.Q	TRUE	show heterogeneity statistic Q in forest plots
forest.pval.Q	TRUE	show p-value of test for heterogeneity in forest plots
forest.Rb	FALSE	do not show heterogeneity statistic Rb in forest plots
digits.I2	0	number of digits for I-squared measure
digits.pval	2	number of digits for p-values
CIbracket,	"("
CIseparator	" to "	print confidence intervals as "(. to .)"
hetlab,		"Test for heterogeneity: "
header.line,	TRUE	print header line

JAMA settings:

Argument	Value	Comment
layout	"JAMA"	layout for forest plots
test.overall	TRUE	print information on test of overall effect
test.subgroup	FALSE	print information on test for subgroup differences
test.effect.subgroup	FALSE	print information on test for effect in subgroups
forest.I2	TRUE	show heterogeneity statistic I2 in forest plots
forest.tau2	FALSE	do not show between-study heterogeneity
		variance in forest plots
forest.tau	FALSE	do not show between-study heterogeneity
		standard deviation in forest plots
forest.Q	TRUE	show heterogeneity statistic Q in forest plots
forest.pval.Q	TRUE	show p-value of test for heterogeneity in forest plots
forest.Rb	FALSE	do not show heterogeneity statistic Rb in forest plots
digits.I2	0	number of digits for I-squared measure
digits.pval	3	number of digits for p-values
CIbracket,	"("
CIseparator	"-"	print confidence intervals as "(.-.)"
zero.pval,	FALSE	print p-values with leading zero
JAMA.pval,	TRUE	round p-values to three digits (for 0.001 < p \le 0.01)
		or two digits (p > 0.01)
header.line,	TRUE	print header line

IQWiG, General Methods 5 settings:

Argument	Value	Comment
method.random.ci	"HK"	Hartung-Knapp method
prediction	TRUE	Prediction interval

IQWiG, General Methods 6 settings:

Argument	Value	Comment
method.random.ci	"HK"	Hartung-Knapp method
adhoc.hakn.ci	"IQWiG6"	ad hoc variance correction
method.tau	"PM"	Paule-Mandel estimator for between-study variance
prediction	TRUE	Prediction interval

Settings for gene expression data:

Argument	Value	Comment
scientific.pval	TRUE	Scientific notation for p-values
method.tau.ci	FALSE	no confidence interval for between-study
		heterogeneity variance

Settings for meta, version 4 or below:

Argument	Value	Comment
method.tau	"DL"	DerSimonian-Laird estimator
method.I2	"Q"	Use Q to calculate I-squared
method.predict	"HTS"	prediction interval with k-2 degrees
		of freedom
exact.smd	FALSE	Use exact formula for standardised mean
		difference (White and Thomas, 2005)
text.common	"Fixed effect model"
text.w.common	"fixed"
warn.deprecated	FALSE	Do not print warnings for deprecated
		arguments

Settings for meta, version 7.0-0 or below:

Argument	Value	Comment
method.tau	"REML"	REML estimator
method.I2	"Q"	Use Q to calculate I-squared
method.predict	"HTS"	prediction interval with k-2 degrees
		of freedom
exact.smd	TRUE	Use exact formula for standardised mean
		difference (White and Thomas, 2005)
text.common	"Common effect model"
text.w.common	"common"
warn.deprecated	FALSE	Do not print warnings for deprecated
		arguments

A list of all arguments with current settings is printed using the command settings.meta().

In order to reset all settings of R package meta the command settings.meta(reset = TRUE) can be used.

Author(s)

Guido Schwarzer [e-mail]

References

White IR, Thomas J (2005): Standardized mean differences in individually-randomized and cluster-randomized trials, with applications to meta-analysis. Clinical Trials, 2, 141–51

See Also

gs, forest.meta, print.meta, labels.meta

Examples

# Get listing of current settings
#
settings.meta()

# Meta-analyses using default settings
#
metabin(10, 20, 15, 20)
metaprop(4, 20)
metabin(10, 20, 15, 20, sm = "RD")
metaprop(4, 20, sm = "PLN")

# Change summary measure for R functions metabin and metaprop
# and store old settings
#
oldset <- settings.meta(smbin = "RD", smprop = "PLN")
#
metabin(10, 20, 15, 20)
metaprop(4, 20)

# Use old settings
#
settings.meta(oldset)

# Change level used to calculate confidence intervals
# (99%-CI for studies, 99.9%-CI for pooled effects)
#
metagen(1:3, 2:4 / 10, sm = "MD")
settings.meta(level = 0.99, level.ma = 0.999)
metagen(1:3, 2:4 / 10, sm = "MD")

# Always print a prediction interval
#
settings.meta(prediction = TRUE)
metagen(1:3, 2:4 / 10, sm = "MD")
metagen(4:6, 4:2 / 10, sm = "MD")

# Try to set unknown argument results in a warning
#
try(settings.meta(unknownarg = TRUE))

# Reset to default settings of R package meta
#
settings.meta("reset")
metabin(10, 20, 15, 20)
metaprop(4, 20)
metagen(1:3, 2:4 / 10, sm = "MD")

# Do not back transform results (e.g. print log odds ratios instead
# of odds ratios, print transformed correlations / proportions
# instead of correlations / proportions)
#
settings.meta(backtransf = FALSE)
metabin(10, 20, 15, 20)
metaprop(4, 20)
metacor(c(0.85, 0.7, 0.95), c(20, 40, 10))

# Forest plot using RevMan 5 style
#
settings.meta("RevMan5")
forest(metagen(1:3, 2:4 / 10, sm = "MD", common = FALSE),
  label.left = "Favours A", label.right = "Favours B",
  colgap.studlab = "2cm", colgap.forest.left = "0.2cm")

# Forest plot using JAMA style
#
settings.meta("JAMA")
forest(metagen(1:3, 2:4 / 10, sm = "MD", common = FALSE),
  label.left = "Favours A", label.right = "Favours B",
  colgap.studlab = "2cm", colgap.forest.left = "0.2cm")

# Use slightly different layout for confidence intervals
# (especially useful if upper confidence limit can be negative)
#
settings.meta(CIseparator = " - ")
forest(metagen(-(1:3), 2:4 / 10, sm = "MD", common = FALSE),
  label.left = "Favours A", label.right = "Favours B",
  colgap.studlab = "2cm", colgap.forest.left = "0.2cm")

# Use old settings
#
settings.meta(oldset)

meta documentation built on Oct. 31, 2024, 5:07 p.m.