Package 'meta'

meta: Brief overview of methods and general hints

Description

R package meta is a user-friendly general package providing standard methods for meta-analysis and supporting Schwarzer et al. (2015), https://link.springer.com/book/10.1007/978-3-319-21416-0.

Details

R package meta (Schwarzer, 2007; Balduzzi et al., 2019) provides the following statistical methods for meta-analysis.

1. Common effect (also called fixed effect) and random effects model:

   • Meta-analysis of continuous outcome data (metacont)

   • Meta-analysis of binary outcome data (metabin)

   • Meta-analysis of incidence rates (metainc)

   • Generic inverse variance meta-analysis (metagen)

   • Meta-analysis of single correlations (metacor)

   • Meta-analysis of single means (metamean)

   • Meta-analysis of single proportions (metaprop)

   • Meta-analysis of single incidence rates (metarate)

2. Several plots for meta-analysis:

   • Forest plot (forest.meta, forest.metabind)

   • Funnel plot (funnel.meta)

   • Galbraith plot / radial plot (radial.meta)

   • L'Abbe plot for meta-analysis with binary outcome data (labbe.metabin, labbe.default)

   • Baujat plot to explore heterogeneity in meta-analysis (baujat.meta)

   • Bubble plot to display the result of a meta-regression (bubble.metareg)

3. Three-level meta-analysis model (Van den Noortgate et al., 2013)

4. Generalised linear mixed models (GLMMs) for binary and count data (Stijnen et al., 2010) (metabin, metainc, metaprop, and metarate)

5. Various estimators for the between-study variance $\tau^2$ in a random effects model (Veroniki et al., 2016); see description of argument method.tau below

6. Two methods to estimate the I-squared statistic (Higgins and Thompson, 2002); see description of argument method.I2 below

7. Hartung-Knapp method for random effects meta-analysis (Hartung & Knapp, 2001a,b), see description of arguments method.random.ci and adhoc.hakn.ci below

8. Kenward-Roger method for random effects meta-analysis (Partlett and Riley, 2017), see description of arguments method.random.ci and method.predict below

9. Prediction interval for the treatment effect of a new study (Veroniki et al., 2019; Higgins et al., 2009; Partlett and Riley, 2017; Nagashima et al., 2019), see description of argument method.predict below

10. Statistical tests for funnel plot asymmetry (metabias.meta, metabias.rm5) and trim-and-fill method (trimfill.meta, trimfill.default) to evaluate bias in meta-analysis

11. Meta-regression (metareg)

12. Cumulative meta-analysis (metacum) and leave-one-out meta-analysis (metainf)

13. Import data from RevMan Web (read.cdir), RevMan 5 (read.rm5), see also metacr to conduct meta-analysis for a single comparison and outcome from a Cochrane review

R package meta provides two vignettes:

• vignette("meta-workflow") with an overview of main functions,

• vignette("meta-tutorial") with up-to-date commands for Balduzzi et al. (2019).

Additional statistical meta-analysis methods are provided by add-on R packages:

• Frequentist methods for network meta-analysis (R package netmeta)

• Statistical methods for sensitivity analysis in meta-analysis (R package metasens)

• Statistical methods for meta-analysis of diagnostic accuracy studies with several cutpoints (R package diagmeta)

In the following, more details on available and default statistical meta-analysis methods are provided and R function settings.meta is briefly described which can be used to change the default settings. Additional information on meta-analysis objects and available summary measures can be found on the help pages meta-object and meta-sm.

Estimation of between-study variance

The following methods are available in all meta-analysis functions to estimate the between-study variance $\tau^2$.

Argument	Method
method.tau = "REML"	Restricted maximum-likelihood estimator (Viechtbauer, 2005)
	(default)
method.tau = "PM"	Paule-Mandel estimator (Paule and Mandel, 1982)
method.tau = "DL"	DerSimonian-Laird estimator (DerSimonian and Laird, 1986)
method.tau = "ML"	Maximum-likelihood estimator (Viechtbauer, 2005)
method.tau = "HS"	Hunter-Schmidt estimator (Hunter and Schmidt, 2015)
method.tau = "SJ"	Sidik-Jonkman estimator (Sidik and Jonkman, 2005)
method.tau = "HE"	Hedges estimator (Hedges and Olkin, 1985)
method.tau = "EB"	Empirical Bayes estimator (Morris, 1983)

For GLMMs, only the maximum-likelihood method is available.

Historically, the DerSimonian-Laird method was the de facto standard to estimate the between-study variance $\tau^2$ and is the default in some software packages including Review Manager 5 (RevMan 5) and R package meta, version 4 and below. However, its role has been challenged and especially the REML and Paule-Mandel estimators have been recommended (Veroniki et al., 2016; Langan et al., 2019). Accordingly, the currenct default in R package meta is the REML estimator.

The following R command could be used to employ the Paule-Mandel instead of the REML estimator in all meta-analyses of the current R session:

• settings.meta(method.tau = "PM")

Other estimators for $\tau^2$ could be selected in a similar way.

Note, for binary outcomes, two variants of the DerSimonian-Laird estimator are available if the Mantel-Haenszel method is used for pooling. If argument Q.Cochrane = TRUE (default), the heterogeneity statistic Q is based on the Mantel-Haenszel instead of the inverse variance estimator under the common effect model. This is the estimator for $\tau^2$ implemented in RevMan 5.

Estimation of I-squared statistic

The following methods are available in all meta-analysis functions to estimate the I-squared statistic (Higgins and Thompson, 2002).

Argument	Method
method.I2 = "Q"	Based on heterogeneity statistic Q (default)
method.I2 = "tau2"	Based on between-study variance $\tau^2$

Using method.I2 = "Q" (Higgins and Thompson, 2002, section 3.3), the value of I$^2$ does not change if the estimate of $\tau^2$ changes. Furthermore, the value of I$^2$ and the test of heterogeneity based on the Q statistic are in agreement. R package metafor uses the second method (method.I2 = "tau2") which is described in Higgins and Thompson (2002), section 3.2. This method is more general in the way that the value of I$^2$ changes with the estimate of $\tau^2$.

Confidence interval for random effects estimate

The following methods are available in all meta-analysis functions to calculate a confidence interval for the random effects estimate.

Argument	Method
method.random.ci = "classic"	Based on standard normal quantile
	(DerSimonian and Laird, 1986) (default)
method.random.ci = "HK"	Method by Hartung and Knapp (2001a/b)
method.random.ci = "KR"	Kenward-Roger method (Partlett and Riley, 2017)

DerSimonian and Laird (1986) introduced the classic random effects model using a quantile of the standard normal distribution to calculate a confidence interval for the random effects estimate. This method implicitly assumes that the weights in the random effects meta-analysis are not estimated but given. Particularly, the uncertainty in the estimation of the between-study variance $\tau^2$ is ignored.

Hartung and Knapp (2001a,b) proposed an alternative method for random effects meta-analysis based on a refined variance estimator for the treatment estimate and a quantile of a t-distribution with k-1 degrees of freedom where k corresponds to the number of studies in the meta-analysis.

The Kenward-Roger method is only available for the REML estimator (method.tau = "REML") of the between-study variance $\tau^2$ (Partlett and Riley, 2017). This method is based on an adjusted variance estimate for the random effects estimate. Furthermore, a quantile of a t-distribution with adequately modified degrees of freedom is used to calculate the confidence interval.

For GLMMs and three-level models, the Kenward-Roger method is not available, but a method similar to Knapp and Hartung (2003) is used if method.random.ci = "HK". For this method, the variance estimator is not modified, however, a quantile of a t-distribution with k-1 degrees of freedom is used; see description of argument test in rma.glmm and rma.mv.

Simulation studies (Hartung and Knapp, 2001a,b; IntHout et al., 2014; Langan et al., 2019) show improved coverage probabilities of the Hartung-Knapp method compared to the classic random effects method. However, in rare settings with very homogeneous treatment estimates, the Hartung-Knapp variance estimate can be arbitrarily small resulting in a very narrow confidence interval (Knapp and Hartung, 2003; Wiksten et al., 2016). In such cases, an ad hoc variance correction has been proposed by utilising the variance estimate from the classic random effects model with the Hartung-Knapp method (Knapp and Hartung, 2003; IQWiQ, 2022). An alternative ad hoc approach is to use the confidence interval of the classic common or random effects meta-analysis if it is wider than the interval from the Hartung-Knapp method (Wiksten et al., 2016; Jackson et al., 2017).

Argument adhoc.hakn.ci can be used to choose the ad hoc correction for the Hartung-Knapp (HK) method:

Argument	Ad hoc method
adhoc.hakn.ci = ""	no ad hoc correction (default)
adhoc.hakn.ci = "se"	use variance correction if HK standard error is smaller
	than standard error from classic random effects
	meta-analysis (Knapp and Hartung, 2003)
adhoc.hakn.ci = "IQWiG6"	use variance correction if HK confidence interval
	is narrower than CI from classic random effects model
	with DerSimonian-Laird estimator (IQWiG, 2022)
adhoc.hakn.ci = "ci"	use wider confidence interval of classic random effects
	and HK meta-analysis
	(Hybrid method 2 in Jackson et al., 2017)

For GLMMs and three-level models, the ad hoc variance corrections are not available.

Prediction interval

The following methods are available in all meta-analysis functions to calculate a prediction interval for the treatment effect in a single new study.

Argument	Method
method.predict = "V"	Based on t-distribution with k-1 degrees of freedom
	(Veroniki et al., 2019) (default)
method.predict = "HTS"	Based on t-distribution with k-2 degrees of freedom
	(Higgins et al., 2009)
method.predict = "HK"	Based on Hartung-Knapp standard error and
	t-distribution with k-1 degrees of freedom
method.predict = "HK-PR"	Based on Hartung-Knapp standard error and
	t-distribution with k-2 degrees of freedom
	(Partlett and Riley, 2017)
method.predict = "KR"	Based on Kenward-Roger standard error and
	t-distribution with approximate Kenward-Roger
	degrees of freedom
method.predict = "KR-PR"	Based on Kenward-Roger standard error and
	t-distribution with approximate Kenward-Roger
	degrees of freedom minus 1 (Partlett and Riley, 2017)
method.predict = "NNF"	Bootstrap approach (Nagashima et al., 2019)
method.predict = "S"	Based on standard normal quantile (Skipka, 2006)

By default (method.predict = "V"), the prediction interval is based on a t-distribution with k-1 degrees of freedom where k corresponds to the number of studies in the meta-analysis (Veroniki et al., 2019). The method by Higgins et al., (2009), which is based on a t-distribution with k-2 degrees of freedom, has been the default in R package meta, version 7.0-0 or lower.

The Hartung-Knapp prediction intervals are also based on a t-distribution, however, use a different standard error.

The Kenward-Roger method is only available for the REML estimator (method.tau = "REML") of the between-study variance $\tau^2$ (Partlett and Riley, 2017). This method is based on an adjusted variance estimate for the random effects estimate. Furthermore, a quantile of a t-distribution with adequately modified degrees of freedom is used to calculate the prediction interval.

The bootstrap approach is only available if R package pimeta is installed (Nagashima et al., 2019). Internally, the pima function is called with argument method = "boot". Argument seed.predict can be used to get a reproducible bootstrap prediction interval and argument seed.predict.subgroup for reproducible bootstrap prediction intervals in subgroups.

The method of Skipka (2006) ignores the uncertainty in the estimation of the between-study variance $\tau^2$ and thus has too narrow limits for meta-analyses with a small number of studies.

For GLMMs and three-level models, only the methods by Veroniki et al. (2019), Higgins et al. (2009) and Skipka (2006) are available. Argument method.predict = "V" in R package meta gives the same prediction intervals as R functions rma.glmm or rma.mv with argument test = "t".

Note, in R package meta, version 7.0-0 or lower, the methods method.predict = "HK-PR" and method.predict = "KR-PR" have been available as method.predict = "HK" and method.predict = "KR".

Argument adhoc.hakn.pi can be used to choose the ad hoc correction for the Hartung-Knapp method:

Argument	Ad hoc method
adhoc.hakn.pi = ""	no ad hoc correction (default)
adhoc.hakn.pi = "se"	use variance correction if HK standard error is smaller

Confidence interval for the between-study variance

The following methods are available in all meta-analysis functions to calculate a confidence interval for $\tau^2$ and $\tau$.

Argument	Method
method.tau.ci = "J"	Method by Jackson (2013)
method.tau.ci = "BJ"	Method by Biggerstaff and Jackson (2008)
method.tau.ci = "QP"	Q-Profile method (Viechtbauer, 2007)
method.tau.ci = "PL"	Profile-Likelihood method for three-level
	meta-analysis model (Van den Noortgate et al., 2013)
method.tau.ci = ""	No confidence interval

The first three methods have been recommended by Veroniki et al. (2016). By default, the Jackson method is used for the DerSimonian-Laird estimator of $\tau^2$ and the Q-profile method for all other estimators of $\tau^2$.

The Profile-Likelihood method is the only method available for the three-level meta-analysis model.

For GLMMs, no confidence intervals for $\tau^2$ and $\tau$ are calculated.

Change default settings for R session

R function settings.meta can be used to change the previously described and several other default settings for the current R session.

Some pre-defined general settings are available:

• settings.meta("RevMan5")

• settings.meta("JAMA")

• settings.meta("BMJ")

• settings.meta("IQWiG5")

• settings.meta("IQWiG6")

• settings.meta("geneexpr")

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 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 third command can be used to generate forest plots in the current layout of the British Medical Journal.

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

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

See settings.meta for more details on these pre-defined general settings.

In addition, settings.meta can be used to define individual settings for the current R session. For example, the following R command specifies the use of Hartung-Knapp and Paule-Mandel method, and the printing of prediction intervals for any meta-analysis generated after execution of this command:

• settings.meta(method.random.ci = "HK", method.tau = "PM", prediction = TRUE)

Data sets

The following data sets are available in R package meta.

Data set	Description
Fleiss1993bin	Aspirin after myocardial infarction
Fleiss1993cont	Mental health treatment on medical utilisation
Olkin1995	Thrombolytic therapy after acute myocardial infarction
Pagliaro1992	Prevention of first bleeding in cirrhosis
amlodipine	Amlodipine for work capacity
caffeine	Caffeine for daytime drowsiness (Cochrane Practice review)
cisapride	Cisapride in non-ulcer dispepsia
lungcancer	Smoking example
smoking	Smoking example
woodyplants	Elevated CO$_2$ and total biomass of woody plants

R package metadat has a large collection of meta-analysis data sets.

Note

Balduzzi et al. (2019) is the preferred citation in publications for meta. Type citation("meta") for a BibTeX entry of this publication.

Type help(package = "meta") for a listing of all R functions and datasets available in meta. For example, results of several meta-analyses can be combined with metabind which is useful to generate a forest plot with results of several subgroup analyses.

R package meta imports R functions from metafor (Viechtbauer, 2010) to

• estimate the between-study variance $\tau^2$,

• conduct meta-regression,

• estimate three-level models,

• estimate generalised linear mixed models.

To report problems and bugs

• type bug.report(package = "meta") if you do not use RStudio,

• send an email to Guido Schwarzer [email protected] if you use RStudio.

The development version of meta is available on GitHub https://github.com/guido-s/meta/.

Author(s)

Guido Schwarzer [email protected]

References

Balduzzi S, Rücker G, Schwarzer G (2019): How to perform a meta-analysis with R: a practical tutorial. Evidence-Based Mental Health, 22, 153–160

Biggerstaff BJ, Jackson D (2008): The exact distribution of Cochran’s heterogeneity statistic in one-way random effects meta-analysis. Statistics in Medicine, 27, 6093–110

DerSimonian R & Laird N (1986): Meta-analysis in clinical trials. Controlled Clinical Trials, 7, 177–88

Hartung J, Knapp G (2001a): On tests of the overall treatment effect in meta-analysis with normally distributed responses. Statistics in Medicine, 20, 1771–82

Hartung J, Knapp G (2001b): A refined method for the meta-analysis of controlled clinical trials with binary outcome. Statistics in Medicine, 20, 3875–89

Hedges LV & Olkin I (1985): Statistical methods for meta-analysis. San Diego, CA: Academic Press

Higgins JPT & Thompson SG (2002): Quantifying heterogeneity in a meta-analysis. Statistics in Medicine, 21, 1539–58

Higgins JPT, Thompson SG, Spiegelhalter DJ (2009): A re-evaluation of random-effects meta-analysis. Journal of the Royal Statistical Society: Series A, 172, 137–59

Hunter JE & Schmidt FL (2015): Methods of Meta-Analysis: Correcting Error and Bias in Research Findings (Third edition). Thousand Oaks, CA: Sage

IntHout J, Ioannidis JPA, Borm GF (2014): The Hartung-Knapp-Sidik-Jonkman method for random effects meta-analysis is straightforward and considerably outperforms the standard DerSimonian-Laird method. BMC Medical Research Methodology, 14, 25

IQWiG (2022): General Methods: Version 6.1. https://www.iqwig.de/en/about-us/methods/methods-paper/

Jackson D (2013): Confidence intervals for the between-study variance in random effects meta-analysis using generalised Cochran heterogeneity statistics. Research Synthesis Methods, 4, 220–229

Jackson D, Law M, Rücker G, Schwarzer G (2017): The Hartung-Knapp modification for random-effects meta-analysis: A useful refinement but are there any residual concerns? Statistics in Medicine, 36, 3923–34

Knapp G & Hartung J (2003): Improved tests for a random effects meta-regression with a single covariate. Statistics in Medicine, 22, 2693–710

Langan D, Higgins JPT, Jackson D, Bowden J, Veroniki AA, Kontopantelis E, et al. (2019): A comparison of heterogeneity variance estimators in simulated random-effects meta-analyses. Research Synthesis Methods, 10, 83–98

Schwarzer G (2007): meta: An R package for meta-analysis. R News, 7, 40–5

Schwarzer G, Carpenter JR and Rücker G (2015): Meta-Analysis with R (Use-R!). Springer International Publishing, Switzerland

Skipka G (2006): The inclusion of the estimated inter-study variation into forest plots for random effects meta-analysis - a suggestion for a graphical representation [abstract]. XIV Cochrane Colloquium, Dublin, 23-26.

Stijnen T, Hamza TH, Ozdemir P (2010): Random effects meta-analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data. Statistics in Medicine, 29, 3046–67

Veroniki AA, Jackson D, Viechtbauer W, Bender R, Bowden J, Knapp G, et al. (2016): Methods to estimate the between-study variance and its uncertainty in meta-analysis. Research Synthesis Methods, 7, 55–79

Veroniki AA, Jackson D, Bender R, Kuss O, Higgins JPT, Knapp G, Salanti G (2019): Methods to calculate uncertainty in the estimated overall effect size from a random-effects meta-analysis. Research Synthesis Methods, 10, 23–43

Van den Noortgate W, López-López JA, Marín-Martínez F, Sánchez-Meca J (2013): Three-level meta-analysis of dependent effect sizes. Behavior Research Methods, 45, 576–94

Viechtbauer W (2005): Bias and efficiency of meta-analytic variance estimators in the random-effects model. Journal of Educational and Behavioral Statistics, 30, 261–93

Viechtbauer W (2007): Confidence intervals for the amount of heterogeneity in meta-analysis. Statistics in Medicine, 26, 37–52

Viechtbauer W (2010): Conducting Meta-Analyses in R with the metafor Package. Journal of Statistical Software, 36, 1–48

Wiksten A, Rücker G, Schwarzer G (2016): Hartung-Knapp method is not always conservative compared with fixed-effect meta-analysis. Statistics in Medicine, 35, 2503–15

See Also

meta-object, meta-sm

---

Amlodipine for Work Capacity

Description

Meta-analysis on the effect of amlodipine on work capacity.

This meta-analysis is used as a data example in Hartung and Knapp (2001).

Format

A data frame with the following columns:

study	study label
n.amlo	number of observations in amlodipine group
mean.amlo	estimated mean in amlodipine group
var.amlo	variance in amlodipine group
n.plac	number of observations in placebo group
mean.plac	estimated mean in placebo group
var.plac	variance in placebo group

Source

Hartung J & Knapp G (2001): On tests of the overall treatment effect in meta-analysis with normally distributed responses. Statistics in Medicine, 20, 1771–82

See Also

metacont

Examples

data(amlodipine)

m <- metacont(n.amlo, mean.amlo, sqrt(var.amlo),
  n.plac, mean.plac, sqrt(var.plac),
  data = amlodipine, studlab = study,
  method.tau = "DL")
m.hk <- update(m, method.random.ci = "HK")

# Same results for mean difference as in Table III in Hartung and
# Knapp (2001)
#
vars.common <- c("TE.common", "lower.common", "upper.common")
vars.random <- c("TE.random", "lower.random", "upper.random")
#
res.common <- as.data.frame(m[vars.common])
names(res.common) <- vars.random
#
res.md <- rbind(res.common,
  as.data.frame(m[vars.random]),
  as.data.frame(m.hk[vars.random]))
#
res.md <- round(res.md, 5)
#
row.names(res.md) <- c("CE", "RE", "RE (HaKn)")
names(res.md) <- c("Absolute difference", "CI lower", "CI upper")
#
res.md

---

Additional functions for objects of class meta

Description

The as.data.frame method returns a data frame containing information on individual studies, e.g., estimated treatment effect and its standard error.

Usage

## S3 method for class 'meta'
as.data.frame(x, row.names = NULL, optional = FALSE, ...)

Arguments

x	An object of class meta.
row.names	NULL or a character vector giving the row names for the data frame.
optional	logical. If TRUE, setting row names and converting column names (to syntactic names) is optional.
...	other arguments

Value

A data frame is returned by the function as.data.frame.

Author(s)

Guido Schwarzer [email protected]

See Also

metabin, metacont, metagen, forest.meta

Examples

data(Fleiss1993cont)
#
# Generate additional variable with grouping information
#
Fleiss1993cont$group <- c(1, 2, 1, 1, 2)
#
# Do meta-analysis without grouping information
#
m1 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
  data = Fleiss1993cont, sm = "SMD", studlab = paste(study, year))
#
# Update meta-analysis object and do subgroup analyses
#
update(m1, subgroup = group)

# Same result using metacont function directly
#
m2 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
  data = Fleiss1993cont, sm = "SMD", studlab = paste(study, year),
  subgroup = group)
m2

# Compare printout of the following two commands
#
as.data.frame(m1)
m1$data

---

Produce weighted bar plot of risk of bias assessment

Description

Produce weighted bar plot of risk of bias assessment

Usage

## S3 method for class 'rob'
barplot(
  height,
  overall = FALSE,
  weighted = TRUE,
  colour = "cochrane",
  quiet = FALSE,
  ...
)

Arguments

height	An object of class rob.
overall	A logical indicating whether to include a bar for overall risk of bias in the figure.
weighted	A logical indicating whether weights should be used in the bar plot.
colour	Specify colour scheme for the bar plot; see rob_summary.
quiet	A logical to suppress the display of the bar plot.
...	Additional arguments (ignored)

Details

This is a wrapper function for rob_summary of R package robvis to produce a weighted bar plot of risk of bias assessment.

Author(s)

Guido Schwarzer [email protected]

See Also

rob, traffic_light, rob_summary

Examples

# Use RevMan 5 settings
oldset <- settings.meta("RevMan5")

data(caffeine)

m1 <- metabin(h.caf, n.caf, h.decaf, n.decaf, sm = "OR",
  data = caffeine, studlab = paste(study, year))

# Add risk of bias assessment to meta-analysis
m2 <- rob(D1, D2, D3, D4, D5, overall = rob, data = m1, tool = "rob2")

# Print risk of bias assessment
rob(m2)

## Not run: 
# Weighted bar plot (if R package robvis has been installed)
barplot(rob(m2))

## End(Not run)

# Use previous settings
settings.meta(oldset)

---

Baujat plot to explore heterogeneity in meta-analysis

Description

Draw a Baujat plot to explore heterogeneity in meta-analysis.

Usage

## S3 method for class 'meta'
baujat(
  x,
  yscale = 1,
  xlim,
  ylim,
  xlab = "Contribution to overall heterogeneity",
  ylab = "Influence on overall result",
  pch = 21,
  cex = 1,
  col = "black",
  bg = "darkgray",
  studlab = TRUE,
  cex.studlab = 0.8,
  pos.studlab,
  offset = 0.5,
  xmin = 0,
  ymin = 0,
  grid = TRUE,
  col.grid = "lightgray",
  lty.grid = "dotted",
  lwd.grid = par("lwd"),
  pty = "s",
  pooled,
  ...
)

Arguments

x	An object of class meta.
yscale	Scaling factor for values on y-axis.
xlim	The x limits (min,max) of the plot.
ylim	The y limits (min,max) of the plot.
xlab	A label for the x-axis.
ylab	A label for the y-axis.
pch	The plotting symbol used for individual studies.
cex	The magnification to be used for plotting symbol.
col	A vector with colour of plotting symbols.
bg	A vector with background colour of plotting symbols (only used if pch in 21:25).
studlab	A logical indicating whether study labels should be printed in the graph. A vector with study labels can also be provided (must be of same length as x$TE then).
cex.studlab	The magnification for study labels.
pos.studlab	Position of study labels, see argument pos in text.
offset	Offset for study labels (see text).
xmin	A numeric specifying minimal value to print study labels (on x-axis).
ymin	A numeric specifying minimal value to print study labels (on y-axis).
grid	A logical indicating whether a grid is printed in the plot.
col.grid	Colour for grid lines.
lty.grid	The line type for grid lines.
lwd.grid	The line width for grid lines.
pty	A character specifying type of plot region (see par).
pooled	A character string indicating whether a common effect or random effects model is used for pooling. Either missing (see Details), "common" or "random", can be abbreviated.
...	Graphical arguments as in par may also be passed as arguments.

Details

Baujat et al. (2002) introduced a scatter plot to explore heterogeneity in meta-analysis. On the x-axis the contribution of each study to the overall heterogeneity statistic (see list object Q of the meta-analysis object x) is plotted. On the y-axis the standardised difference of the overall treatment effect with and without each study is plotted; this quantity describes the influence of each study on the overal treatment effect.

Information from object x is utilised if argument pooled is missing. A common effect model is assumed (pooled="common") if argument x$common is TRUE; a random effects model is assumed (pooled="random") if argument x$random is TRUE and x$common is FALSE.

Internally, the metainf function is used to calculate the values on the y-axis.

Value

A data.frame with the following variables:

x	Coordinate on x-axis (contribution to heterogeneity statistic)
y	Coordinate on y-axis (influence on overall treatment effect)

Author(s)

Guido Schwarzer [email protected]

References

Baujat B, Mahé C, Pignon JP, Hill C (2002): A graphical method for exploring heterogeneity in meta-analyses: Application to a meta-analysis of 65 trials. Statistics in Medicine, 30, 2641–52

See Also

metagen, metainf

Examples

data(Olkin1995)

# Only consider first ten studies
m1 <- metabin(ev.exp, n.exp, ev.cont, n.cont,
  data = Olkin1995, sm = "OR", method = "I", studlab = paste(author, year),
  subset = 1:10)

# Generate Baujat plot
baujat(m1)

## Not run: 
m1 <- metabin(ev.exp, n.exp, ev.cont, n.cont,
  data = Olkin1995, sm = "OR", method = "I", studlab = paste(author, year))

# Do not print study labels if the x-value is smaller than 4 and
# the y-value is smaller than 1
baujat(m1, yscale = 10, xmin = 4, ymin = 1)

# Change position of study labels
baujat(m1, yscale = 10, xmin = 4, ymin = 1,
       pos = 1, xlim = c(0, 6.5))

# Generate Baujat plot and assign x- and y- coordinates to R object
# b1
b1 <- baujat(m1)

# Calculate overall heterogeneity statistic
sum(b1$x)
m1$Q

## End(Not run)

---

Calculate best linear unbiased predictor for meta object

Description

Calculate best linear unbiased predictors (BLUPs) for meta-analysis object created with R package meta.

Usage

## S3 method for class 'meta'
blup(x, level = x$level, backtransf = x$backtransf, ...)

## S3 method for class 'blup.meta'
print(
  x,
  backtransf = attr(x, "x")$backtransf,
  digits = gs("digits"),
  digits.se = gs("digits.se"),
  digits.tau2 = gs("digits.tau2"),
  digits.tau = gs("digits.tau"),
  big.mark = gs("big.mark"),
  se = FALSE,
  print.tau2 = gs("print.tau2"),
  print.tau = gs("print.tau"),
  details = gs("details"),
  ...
)

## S3 method for class 'blup.meta'
estimates(
  x,
  se = FALSE,
  backtransf = attr(x, "x")$backtransf,
  digits = gs("digits"),
  digits.se = gs("digits.se"),
  digits.tau2 = gs("digits.tau2"),
  digits.tau = gs("digits.tau"),
  writexl = !missing(path),
  path = "estimates_blup.xlsx",
  overwrite = FALSE,
  ...
)

## S3 method for class 'estimates.blup.meta'
print(x, big.mark = gs("big.mark"), details = gs("details"), ...)

Arguments

x	An object of class meta, blup.meta, or estimates.blup.meta.
level	The level used to calculate prediction intervals for BLUPs.
backtransf	A logical indicating whether BLUPs should be back transformed. If backtransf = TRUE, results for sm = "OR" will be odds ratios rather than log odds ratios, for example.
...	Additional arguments (passed on to prmatrix).
digits	Minimal number of significant digits, see print.default.
digits.se	Minimal number of significant digits for standard errors.
digits.tau2	Minimal number of significant digits for between-study variance $\tau^2$, see print.default.
digits.tau	Minimal number of significant digits for $\tau$, the square root of the between-study variance $\tau^2$.
big.mark	A character used as thousands separator.
se	A logical indicating whether standard errors should be printed / extracted.
print.tau2	A logical specifying whether between-study variance $\tau^2$ should be printed.
print.tau	A logical specifying whether $\tau$, the square root of the between-study variance $\tau^2$, should be printed.
details	A logical specifying whether details on statistical methods should be printed.
writexl	A logical indicating whether an Excel file should be created (R package writexl must be available).
path	A character string specifying the filename of the Excel file.
overwrite	A logical indicating whether an existing Excel file should be overwritten.

Value

Data frame with variables

studlab	Study label
blup	estimated best linear unbiased predictor
se.blup	standard error (only if argument backtransf = FALSE)
lower	lower prediction limits
upper	upper prediction limits

Author(s)

Guido Schwarzer [email protected]

Examples

data("dat.bcg", package = "metadat")
m1 <- metabin(tpos, tpos + tneg, cpos, cpos + cneg,
  data = dat.bcg, studlab = paste(author, year), method = "Inverse")
summary(m1)
blup(m1)

## Not run: 
estimates(blup(m1), path = "blup_m1.xlsx")

## End(Not run)

---

Bubble plot to display the result of a meta-regression

Description

Draw a bubble plot to display the result of a meta-regression.

Usage

## S3 method for class 'metareg'
bubble(
  x,
  xlim,
  ylim,
  xlab,
  ylab,
  cex,
  min.cex = 0.5,
  max.cex = 5,
  pch = 21,
  col = "black",
  bg = "darkgray",
  lty = 1,
  lwd = 1,
  col.line = "black",
  studlab = FALSE,
  cex.studlab = 0.8,
  pos.studlab = 2,
  offset = 0.5,
  regline = TRUE,
  backtransf = x$.meta$x$backtransf,
  ref,
  col.ref = "lightgray",
  lty.ref = 1,
  lwd.ref = 1,
  pscale = x$.meta$x$pscale,
  irscale = x$.meta$x$irscale,
  axes = TRUE,
  box = TRUE,
  ...
)

bubble(x, ...)

Arguments

x	An object of class metareg.
xlim	The x limits (min,max) of the plot.
ylim	The y limits (min,max) of the plot.
xlab	A label for the x-axis.
ylab	A label for the y-axis.
cex	The magnification to be used for plotting symbols.
min.cex	Minimal magnification for plotting symbols.
max.cex	Maximal magnification for plotting symbols.
pch	The plotting symbol(s) used for individual studies.
col	A vector with colour of plotting symbols.
bg	A vector with background colour of plotting symbols (only used if pch in 21:25).
lty	The line type for the meta-regression line.
lwd	The line width for the meta-regression line.
col.line	Colour for the meta-regression line.
studlab	A logical indicating whether study labels should be printed in the graph. A vector with study labels can also be provided (must be of same length as the numer of studies in the meta-analysis then).
cex.studlab	The magnification for study labels.
pos.studlab	Position of study labels, see argument pos in text.
offset	Offset for study labels (see text).
regline	A logical indicating whether a regression line should be added to the bubble plot.
backtransf	A logical indicating whether results for relative summary measures (argument sm equal to "OR", "RR", "HR", or "IRR") should be back transformed. If backtransf=TRUE, results for sm="OR" are printed as odds ratios rather than log odds ratios, for example.
ref	A numerical giving the reference value to be plotted as a line in the bubble plot. No reference line is plotted if argument ref is equal to NA.
col.ref	Colour of the reference line.
lty.ref	The line type for the reference line.
lwd.ref	The line width for the reference line.
pscale	A numeric giving scaling factor for printing of probabilities.
irscale	A numeric defining a scaling factor for printing of incidence rates.
axes	Either a logical or a character string equal to "x", "y" or "xy" indicating whether x- and y-axis should be printed.
box	A logical indicating whether a box should be printed.
...	Graphical arguments as in par may also be passed as arguments.

Details

A bubble plot can be used to display the result of a meta-regression. It is a scatter plot with the treatment effect for each study on the y-axis and the covariate used in the meta-regression on the x-axis. Typically, the size of the plotting symbol is inversely proportional to the variance of the estimated treatment effect (Thompson & Higgins, 2002).

Argument cex specifies the plotting size for each individual study. If this argument is missing the weights from the meta-regression model will be used (which typically is a random effects model). Use cex="common" in order to utilise weights from a common effect model to define the size of the plotted symbols (even for a random effects meta-regression). If a vector with individual study weights is provided, the length of this vector must be of the same length as the number of studies.

Arguments min.cex and max.cex can be used to define the size of the smallest and largest plotting symbol. The plotting size of the most precise study is set to max.cex whereas the plotting size of all studies with a plotting size smaller than min.cex will be set to min.cex.

For a meta-regression with more than one covariate. Only a scatter plot of the first covariate in the regression model is shown. In this case the effect of the first covariate adjusted for other covariates in the meta-regression model is shown.

For a factor or categorial covariate separate bubble plots for each group compared to the baseline group are plotted.

Author(s)

Guido Schwarzer [email protected]

References

Thompson SG, Higgins JP (2002): How should meta-regression analyses be undertaken and interpreted? Statistics in Medicine, 21, 1559–73

See Also

metagen, metainf

Examples

data(Fleiss1993cont)

# Add some (fictitious) grouping variables:
Fleiss1993cont$age <- c(55, 65, 52, 65, 58)
Fleiss1993cont$region <- c("Europe", "Europe", "Asia", "Asia", "Europe")

m1 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
  data = Fleiss1993cont, sm = "SMD")

mr1 <- metareg(m1, region)
mr1

bubble(mr1)
bubble(mr1, lwd = 2, col.line = "blue")

mr2 <- metareg(m1, age)
mr2

bubble(mr2, lwd = 2, col.line = "blue", xlim = c(50, 70))
bubble(mr2, lwd = 2, col.line = "blue", xlim = c(50, 70), cex = "common")

# Do not print regression line
#
bubble(mr2, lwd = 2, col.line = "blue", xlim = c(50, 70), regline = FALSE)

---

Caffeine for daytime drowsiness

Description

Caffeine for daytime drowsiness (Cochrane Practice review)

Format

A data frame with the following columns:

study	study label
year	year of publication
h.caf	Number of participants with headaches (caffeine group)
n.caf	Number of participants (caffeine group)
h.decaf	Number of participants with headaches (decaf group)
n.decaf	Number of participants (decaf group)
D1	Domain 1 of risk of bias 2 tool (RoB 2)
D2	Domain 2 (RoB 2)
D3	Domain 3 (RoB 2)
D4	Domain 4 (RoB 2)
D5	Domain 5 (RoB 2)
rob	Overall RoB 2 assessment

Details

Data come from the Cochrane Practice review on caffeine for daytime drowsiness. Eight fictitous studies evaluate the risk of headaches after drinking either caffeinated or decaffeinated coffee.

References

Higgins JPT, Savović J, Page MJ, Sterne JA on behalf of the RoB2 Development Group (2019): Revised Cochrane risk-of-bias tool for randomized trials. https://www.riskofbias.info/welcome/rob-2-0-tool

See Also

metabin, rob

Examples

oldset <- settings.meta("RevMan5")

data(caffeine)
head(caffeine)

m1 <- metabin(h.caf, n.caf, h.decaf, n.decaf, sm = "OR",
  data = caffeine, studlab = paste(study, year))

# Add risk of bias assessment to meta-analysis
m1 <- rob(D1, D2, D3, D4, D5, overall = rob, data = m1, tool = "rob2")

# Print risk of bias assessment
rob(m1)

# Forest plot with risk of bias assessment
forest(m1)

settings.meta(oldset)

---

Calculation of confidence intervals (based on normal approximation or t-distribution)

Description

Calculation of confidence intervals; based on normal approximation or t-distribution.

Usage

ci(TE, seTE, level = 0.95, df = NULL, null.effect = 0)

Arguments

TE	Estimated treatment effect.
seTE	Standard error of treatment estimate.
level	The confidence level required.
df	Degrees of freedom (for confidence intervals based on t-distribution).
null.effect	A numeric value specifying the effect under the null hypothesis.

Value

List with components

TE	Estimated treatment effect
seTE	Standard error of treatment estimate
lower	Lower confidence limits
upper	Upper confidence limits
statistic	Test statistic (either z-score or t-score)
p	P-value of text.with null hypothesis TE=0
level	The confidence level required
df	Degrees of freedom (t-distribution)

Note

This function is primarily called from other functions of the library meta, e.g. forest.meta, summary.meta.

Author(s)

Guido Schwarzer [email protected]

Examples

data.frame(ci(170, 10))
data.frame(ci(170, 10, 0.99))
data.frame(ci(1.959964, 1))
data.frame(ci(2.2621571628, 1, df = 9))

---

Cisapride in Non-Ulcer Dispepsia

Description

Meta-analysis on cisapride in non-ulcer dispepsia.

This meta-analysis is used as a data example in Hartung and Knapp (2001).

Format

A data frame with the following columns:

study	study label
event.cisa	number of events in cisapride group
n.cisa	number of observations in cisapride group
event.plac	number of events in placebo group
n.plac	number of observations in placebo group

Source

Hartung J & Knapp G (2001): A refined method for the meta-analysis of controlled clinical trials with binary outcome. Statistics in Medicine, 20, 3875–89

See Also

metabin

Examples

data(cisapride)

m.or <- metabin(event.cisa, n.cisa, event.plac, n.plac,
  data = cisapride, sm = "OR",
  method = "Inverse", method.tau = "DL",
  studlab = study, method.incr = "all")

m.or.hk <- update(m.or, method.random.ci = "HK")
m.rr <- update(m.or, sm = "RR")
m.rr.hk <- update(m.or, sm = "RR", method.random.ci = "HK")

vars.common <- c("TE.common", "lower.common", "upper.common")
vars.random <- c("TE.random", "lower.random", "upper.random")
#
res.common.or <- as.data.frame(m.or[vars.common])
names(res.common.or) <- vars.random
#
res.common.rr <- as.data.frame(m.rr[vars.common])
names(res.common.rr) <- vars.random

# Results for log risk ratio - see Table VII in Hartung and Knapp (2001) 
#
res.rr <- rbind(res.common.rr,
  as.data.frame(m.rr[vars.random]),
  as.data.frame(m.rr.hk[vars.random]))
#
row.names(res.rr) <- c("CE", "RE", "RE (HaKn)")
names(res.rr) <- c("Log risk ratio", "CI lower", "CI upper")
#
res.rr


# Results for log odds ratio (Table VII in Hartung and Knapp 2001) 
#
res.or <- rbind(res.common.or,
  as.data.frame(m.or[vars.random]),
  as.data.frame(m.or.hk[vars.random]))
#
row.names(res.or) <- c("CE", "RE", "RE (HaKn)")
names(res.or) <- c("Log odds ratio", "CI lower", "CI upper")
#
res.or

---

Drapery plot

Description

Draw a drapery plot with (scaled) p-value curves for individual studies and meta-analysis estimates.

Usage

drapery(
  x,
  type = "zvalue",
  layout = "grayscale",
  study.results = TRUE,
  lty.study = 1,
  lwd.study = 1,
  col.study = "darkgray",
  labels,
  col.labels = "black",
  cex.labels = 0.7,
  subset.labels,
  srt.labels,
  common = x$common,
  random = x$random,
  lty.common = 1,
  lwd.common = max(3, lwd.study),
  col.common = "blue",
  lty.random = 1,
  lwd.random = lwd.common,
  col.random = "red",
  sign = NULL,
  lty.sign = 1,
  lwd.sign = 1,
  col.sign = "black",
  prediction = random,
  col.predict = "lightblue",
  alpha = if (type == "zvalue") c(0.001, 0.01, 0.05, 0.1) else c(0.01, 0.05, 0.1),
  lty.alpha = 2,
  lwd.alpha = 1,
  col.alpha = "black",
  cex.alpha = 0.7,
  col.null.effect = "black",
  legend = TRUE,
  pos.legend = "topleft",
  bg = "white",
  bty = "o",
  backtransf = x$backtransf,
  xlab,
  ylab,
  xlim,
  ylim,
  lwd.max = 2.5,
  lwd.study.weight = if (random) "random" else "common",
  at = NULL,
  n.grid = if (type == "zvalue") 10000 else 1000,
  mar = c(5.1, 4.1, 4.1, 4.1),
  plot = TRUE,
  warn.deprecated = gs("warn.deprecated"),
  fixed,
  lwd.fixed,
  lty.fixed,
  col.fixed,
  ...
)

Arguments

x	An object of class meta.
type	A character string indicating whether to plot test statistics ("zvalue") or p-values ("pvalue"), can be abbreviated.
layout	A character string for the line layout of individual studies: "grayscale", "equal", or "linewidth" (see Details), can be abbreviated.
study.results	A logical indicating whether results for individual studies should be shown in the figure.
lty.study	Line type for individual studies.
lwd.study	Line width for individual studies.
col.study	Colour of lines for individual studies.
labels	A logical or character string indicating whether study labels should be shown at the top of the drapery plot; either FALSE, "id", or "studlab"; see Details.
col.labels	Colour of study labels.
cex.labels	The magnification for study labels.
subset.labels	A vector specifying which study labels should be shown in the drapery plot.
srt.labels	A numerical vector or single numeric (between 0 and 90) specifying the angle to rotate study labels; see Details.
common	A logical indicating whether to show result for the common effect model.
random	A logical indicating whether to show result for the random effects model.
lty.common	Line type for common effect meta-analysis.
lwd.common	Line width for common effect meta-analysis.
col.common	Colour of lines for common effect meta-analysis.
lty.random	Line type for random effects meta-analysis.
lwd.random	Line width for random effects meta-analysis.
col.random	Colour of lines for random effects meta-analysis.
sign	Significance level used to highlight significant values in curves.
lty.sign	Line type for significant values.
lwd.sign	Line width for significant values.
col.sign	Line colour for significant values.
prediction	A logical indicating whether to show prediction region.
col.predict	Colour of prediction region
alpha	Horizonal lines are printed for the specified alpha values.
lty.alpha	Line type of horizonal lines for alpha values.
lwd.alpha	Line width of horizonal lines for alpha values.
col.alpha	Colour of horizonal lines for alpha values.
cex.alpha	The magnification for the text of the alpha
col.null.effect	Colour of vertical line indicating null effect.
legend	A logical indicating whether a legend should be printed.
pos.legend	A character string with position of legend (see legend).
bg	Background colour of legend (see legend).
bty	Type of the box around the legend; either "o" or "n" (see legend).
backtransf	A logical indicating whether results should be back transformed on the x-axis. For example, if backtransf = FALSE, log odds ratios instead of odds ratios are shown on the x-axis.
xlab	A label for the x-axis.
ylab	A label for the y-axis.
xlim	The x limits (min, max) of the plot.
ylim	The y limits (min, max) of the plot (ignored if type = "pvalue").
lwd.max	The maximum line width (only considered if argument layout is equal to "linewidth").
lwd.study.weight	A character string indicating whether to determine line width for individual studies using weights from common effect ("common") or random effects model ("random"), can be abbreviated (only considered if argument layout is equal to "linewidth").
at	Points at which tick-marks are to be drawn on the x-axis.
n.grid	The number of grid points to calculate the p-value or test statistic functions.
mar	Physical plot margin, see par.
plot	A logical indicating whether to generate a figure.
warn.deprecated	A logical indicating whether warnings should be printed if deprecated arguments are used.
fixed	Deprecated argument (replaced by 'common').
lwd.fixed	Deprecated argument (replaced by 'lwd.common').
lty.fixed	Deprecated argument (replaced by 'lty.common').
col.fixed	Deprecated argument (replaced by 'col.common').
...	Graphical arguments as in par may also be passed as arguments.

Details

The concept of a p-value function, also called confidence curve, goes back to Birnbaum (1961). A drapery plot, showing p-value functions (or a scaled version based on the corresponding test statistics) for individual studies as well as meta-analysis estimates, is drawn in the active graphics window. Furthermore, a prediction region for a single future study is shown as a shaded area. In contrast to a forest plot, a drapery plot does not provide information for a single confidence level however for any confidence level.

Argument type can be used to either show p-value functions (Birnbaum, 1961) or a scaled version (Infanger, 2019) with test statistics (default).

Argument layout determines how curves for individual studies are presented:

• darker gray tones with increasing precision (layout = "grayscale")

• thicker lines with increasing precision (layout = "linewidth")

• equal lines (layout = "equal")

Argument labels determines how curves of individual studies are labelled:

• number of the study in the (unsorted) forest plot / printout of a meta-analysis (labels = "id")

• study labels provided by argument studlab in meta-analysis functions (labels = "studlab")

• no study labels (labels = FALSE)

By default, study labels are used (labels = "studlab") if no label has more than three characters; otherwise IDs are used (labels = "id"). The connection between IDs and study labels (among other information) is part of a data frame which is invisibly returned (if argument study.results = TRUE).

Argument srt.labels can be used to change the rotation of IDs or study labels. By default, study labels are rotated by +/- 45 degrees if at least one study label has more than three characters; otherwise labels are not rotated.

If labels = "studlab", labels are rotated by -45 degrees for studies with a treatment estimate below the common effect estimate and otherwise by 45 degrees.

Author(s)

Gerta Rücker [email protected], Guido Schwarzer [email protected]

References

Birnbaum A (1961): Confidence Curves: An Omnibus Technique for Estimation and Testing Statistical Hypotheses. Journal of the American Statistical Association, 56, 246–9

Infanger D and Schmidt-Trucksäss A (2019): P value functions: An underused method to present research results and to promote quantitative reasoning Statistics in Medicine, 38, 4189–97

See Also

forest, radial

Examples

data("lungcancer")
m1 <- metainc(d.smokers, py.smokers, d.nonsmokers, py.nonsmokers,
  data = lungcancer, studlab = study)

# Drapery plot
#
drapery(m1, xlim = c(0.5, 50))

## Not run: 
data(Fleiss1993bin)
m2 <- metabin(d.asp, n.asp, d.plac, n.plac,
  data = Fleiss1993bin, studlab = paste(study, year),
  sm = "OR", random = FALSE)

# Produce drapery plot and print data frame with connection between
# IDs and study labels
#
(drapery(m2))

# For studies with a significant effect (p < 0.05), show
# study labels and print labels and lines in red
#
drapery(m2,
  labels = "studlab", subset.labels = pval < 0.05,
  srt.labels = 0, col.labels = "red",
  col.study = ifelse(pval < 0.05, "red", "darkgray"))

## End(Not run)

---

Extract results from meta-analysis object

Description

Extract study and meta-analysis results from meta-analysis object which can be stored in an Excel file.

Usage

## S3 method for class 'meta'
estimates(
  x,
  sortvar,
  study.results = TRUE,
  common = x$common,
  random = x$random,
  prediction = x$prediction,
  overall = x$overall,
  subgroup,
  prediction.subgroup = x$prediction.subgroup,
  se = FALSE,
  ci = TRUE,
  statistic = FALSE,
  pval = FALSE,
  n = TRUE,
  backtransf = x$backtransf,
  digits = gs("digits"),
  digits.se = gs("digits.se"),
  digits.stat = gs("digits.stat"),
  digits.pval = gs("digits.pval"),
  writexl = !missing(path),
  path = "estimates.xlsx",
  overwrite = FALSE,
  ...
)

estimates(x, ...)

## S3 method for class 'estimates.meta'
print(
  x,
  digits.tau = gs("digits.tau"),
  text.tau2 = gs("text.tau2"),
  text.tau = gs("text.tau"),
  big.mark = gs("big.mark"),
  details = TRUE,
  ...
)

Arguments

x	A meta-analysis object of class meta.
sortvar	An optional vector used to sort the individual studies (must be of same length as x$TE).
study.results	A logical indicating whether study results should be extracted.
common	A logical indicating whether results of common effect meta-analysis should be extracted.
random	A logical indicating whether results of random effects meta-analysis should be extracted.
prediction	A logical indicating whether prediction interval should be extracted.
overall	A logical indicating whether overall summaries should be extracted. This argument is useful in a meta-analysis with subgroups if overall results should not be extracted.
subgroup	A logical indicating whether subgroup results should be extracted.
prediction.subgroup	A single logical or logical vector indicating whether / which prediction intervals should be extracted for subgroups.
se	A logical indicating whether standard errors should be extracted.
ci	A logical indicating whether confidence / prediction interval should be extracted.
statistic	A logical indicating whether to extract statistic of test for overall effect.
pval	A logical indicating whether to extract p-value of test for overall effect.
n	A logical indicating whether sample sizes should be extracted (if available).
backtransf	A logical indicating whether extracted results should be back transformed.
digits	Minimal number of significant digits, see print.default.
digits.se	Minimal number of significant digits for standard errors, see print.default.
digits.stat	Minimal number of significant digits for z- or t-statistic for test of overall effect, see print.default.
digits.pval	Minimal number of significant digits for p-value of overall treatment effect, see print.default.
writexl	A logical indicating whether an Excel file should be created (R package writexl must be available).
path	A character string specifying the filename of the Excel file.
overwrite	A logical indicating whether an existing Excel file should be overwritten.
...	Additional arguments passed on to prmatrix.
digits.tau	Minimal number of significant digits for square root of between-study variance, see print.default.
text.tau2	Text printed to identify between-study variance $\tau^2$.
text.tau	Text printed to identify $\tau$, the square root of the between-study variance $\tau^2$.
big.mark	A character used as thousands separator.
details	A logical specifying whether details on statistical methods should be printed.

Details

Extract study and meta-analysis results from meta-analysis object. By default, a data frame with the results is generated. Alternatively, an Excel file is created if argument writexl = TRUE.

The following information is extracted.

Variable	Content
studlab	Study label / descriptor of meta-analysis result
estimate	(Back transformed) estimate for individual studies / meta-analysis
se	Standard error
lower	Lower (back transformed) confidence / prediction interval limit
upper	Upper (back transformed) confidence / prediction interval limit
k	Number of studies
df	Degrees of freedom for confidence / prediction intervals
statistic	Statistic for test of effect
pval	P-value for test of effect
n	Total sample size
n.e	Sample size in first (experimental) group
n.c	Sample size in second (control) group

Some variables are only extracted if the corresponding logical argument se, ci, statistic or n is TRUE. Furthermore, (group) sample sizes are only extracted if available in the meta-analysis object.

The variables estimate, lower and upper contain the back transformed effects and confidence interval limits, e.g., odds ratio (argument sm = "OR" in metabin or metagen) or correlation (sm = "ZCOR" in metacor or metagen), if argument backtransf is TRUE. Otherwise, these variables contain the transformed values, e.g., log odds ratio (sm = "OR") or Fisher's Z transformed correlations (sm = "ZCOR"). See meta-sm for available summary measures and meta-transf for the corresponding transformations and back transformations.

Value

A data frame with additional class 'extract.meta' or an Excel file.

Author(s)

Guido Schwarzer [email protected]

See Also

meta-transf, meta-sm, as.data.frame.meta

Examples

m1 <- metacor(c(0.85, 0.7, 0.95), c(20, 40, 10))
summary(m1)
estimates(m1)
estimates(m1, backtransf = FALSE)
estimates(update(m1, common = FALSE, random = FALSE))
estimates(update(m1, prediction = TRUE))
estimates(update(m1, prediction = TRUE,
  level.ma = 0.99, level.predict = 0.9))

## Not run: 
# Create Excel file with extracted results
# (if R package writexl is available)
#
fname1 <- tempfile(fileext = ".xlsx")
estimates(m1, path = fname1)
# An existing Excel file is not overwritten but a warning is printed
estimates(m1, path = fname1)
# Overwrite an existing Excel file
estimates(m1, path = fname1, overwrite = TRUE)
# Suppress message on file creation and overwrite existing file
suppressMessages(estimates(m1, path = fname1, overwrite = TRUE))

# Save the extracted results in a text file
fname2 <- tempfile(fileext = ".csv")
fname2
write.csv(estimates(m1), file = fname2, row.names = FALSE)

## End(Not run)

---

Aspirin after Myocardial Infarction

Description

Meta-analysis on aspirin in preventing death after myocardial infarction.

Data example in Fleiss (1993) for meta-analysis with binary outcomes.

Format

A data frame with the following columns:

study	study label
year	year of publication
d.asp	number of deaths in aspirin group
n.asp	number of observations in aspirin group
d.plac	number of deaths in placebo group
n.plac	number of observations in placebo group

Source

Fleiss JL (1993): The statistical basis of meta-analysis. Statistical Methods in Medical Research, 2, 121–45

See Also

metabin

Examples

data(Fleiss1993bin)
metabin(d.asp, n.asp, d.plac, n.plac, data = Fleiss1993bin,
  studlab = paste(study, year), sm = "OR", random = FALSE)

---

Mental Health Treatment

Description

Meta-analysis on the Effect of Mental Health Treatment on Medical Utilisation.

Data example in Fleiss (1993) for meta-analysis with continuous outcomes.

Format

A data frame with the following columns:

study	study label
year	year of publication
n.psyc	number of observations in psychotherapy group
mean.psyc	estimated mean in psychotherapy group
sd.psyc	standard deviation in psychotherapy group
n.cont	number of observations in control group
mean.cont	estimated mean in control group
sd.cont	standard deviation in control group

Source

Fleiss JL (1993): The statistical basis of meta-analysis. Statistical Methods in Medical Research, 2, 121–45

See Also

Fleiss1993bin

metacont

Examples

data(Fleiss1993cont)
# Note, the following command uses the bias-corrected version of
# Hedges' g. Accordingly, results differ from Fleiss (1993), section 3,
# using the uncorrected version of Hedges' g.
metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
  data = Fleiss1993cont, studlab = paste(study, year),
  random = FALSE, sm = "SMD")

---

Forest plot to display the result of a meta-analysis

Description

Draw a forest plot (using grid graphics system) in the active graphics window or store the forest plot in a file.

Usage

## S3 method for class 'meta'
forest(
  x,
  sortvar,
  studlab = TRUE,
  layout = gs("layout"),
  common = x$common,
  random = x$random,
  overall = x$overall,
  text.common = x$text.common,
  text.random = x$text.random,
  lty.common = gs("lty.common"),
  lty.random = gs("lty.random"),
  col.common = gs("col.common"),
  col.random = gs("col.random"),
  text.w.common = x$text.w.common,
  text.w.random = x$text.w.random,
  prediction = x$prediction,
  text.predict = x$text.predict,
  subgroup = TRUE,
  subgroup.hetstat = subgroup & (is.character(hetstat) || hetstat),
  print.subgroup.labels = TRUE,
  subgroup.name = x$subgroup.name,
  print.subgroup.name = x$print.subgroup.name,
  sep.subgroup = x$sep.subgroup,
  text.common.w = text.common,
  text.random.w = text.random,
  text.predict.w = text.predict,
  sort.subgroup = gs("sort.subgroup"),
  pooled.totals = common | random,
  pooled.events = gs("pooled.events"),
  pooled.times = gs("pooled.times"),
  study.results = gs("study.results"),
  rob = x$rob,
  rob.text = "Risk of Bias",
  rob.xpos = 0,
  rob.legend = TRUE,
  rob.only = FALSE,
  xlab = "",
  xlab.pos,
  smlab = NULL,
  smlab.pos,
  xlim,
  allstudies = TRUE,
  weight.study = NULL,
  pscale = x$pscale,
  irscale = x$irscale,
  irunit = x$irunit,
  file = NULL,
  width = gs("width"),
  rows.gr = NULL,
  func.gr = NULL,
  args.gr = NULL,
  dev.off = NULL,
  ref,
  lower.equi = gs("lower.equi"),
  upper.equi = gs("upper.equi"),
  lty.equi = gs("lty.equi"),
  col.equi = gs("col.equi"),
  fill.equi = gs("fill.equi"),
  fill.lower.equi = fill.equi,
  fill.upper.equi = rev(fill.equi),
  fill = gs("fill"),
  leftcols = gs("leftcols"),
  rightcols = gs("rightcols"),
  leftlabs = gs("leftlabs"),
  rightlabs = gs("rightlabs"),
  label.e = x$label.e,
  label.c = x$label.c,
  label.e.attach = gs("label.e.attach"),
  label.c.attach = gs("label.c.attach"),
  label.left = x$label.left,
  label.right = x$label.right,
  bottom.lr = gs("bottom.lr"),
  lab.NA = gs("lab.NA"),
  lab.NA.effect = gs("lab.NA.effect"),
  lab.NA.weight = gs("lab.NA.weight"),
  lwd = gs("lwd"),
  at = NULL,
  label = TRUE,
  col.label = gs("col.label"),
  type.study = gs("type.study"),
  type.common = gs("type.common"),
  type.random = type.common,
  type.subgroup = ifelse(study.results, "diamond", "square"),
  type.subgroup.common = type.subgroup,
  type.subgroup.random = type.subgroup,
  col.study = gs("col.study"),
  col.square = gs("col.square"),
  col.square.lines = gs("col.square.lines"),
  col.circle = gs("col.circle"),
  col.circle.lines = col.circle,
  col.inside = gs("col.inside"),
  col.inside.common = col.inside,
  col.inside.random = col.inside,
  col.diamond = gs("col.diamond"),
  col.diamond.common = col.diamond,
  col.diamond.random = col.diamond,
  col.diamond.lines = gs("col.diamond.lines"),
  col.diamond.lines.common = col.diamond.lines,
  col.diamond.lines.random = col.diamond.lines,
  col.predict = gs("col.predict"),
  col.predict.lines = gs("col.predict.lines"),
  col.subgroup = gs("col.subgroup"),
  col.label.left = x$col.label.left,
  col.label.right = x$col.label.right,
  hetstat = common | random | overall.hetstat,
  overall.hetstat = x$overall.hetstat & !inherits(x, "metamerge"),
  hetlab = gs("hetlab"),
  resid.hetstat = gs("resid.hetstat"),
  resid.hetlab = gs("resid.hetlab"),
  print.I2 = gs("forest.I2"),
  print.I2.ci = gs("forest.I2.ci"),
  print.tau2 = gs("forest.tau2"),
  print.tau2.ci = gs("forest.tau2.ci"),
  print.tau = gs("forest.tau"),
  print.tau.ci = gs("forest.tau.ci"),
  print.Q = gs("forest.Q"),
  print.pval.Q = gs("forest.pval.Q"),
  print.Rb = gs("forest.Rb"),
  print.Rb.ci = gs("forest.Rb.ci"),
  text.subgroup.nohet = gs("text.subgroup.nohet"),
  LRT = gs("LRT"),
  test.overall = gs("test.overall"),
  test.overall.common = common & overall & test.overall,
  test.overall.random = random & overall & test.overall,
  label.test.overall.common,
  label.test.overall.random,
  print.stat = gs("forest.stat"),
  test.subgroup = x$test.subgroup,
  test.subgroup.common = test.subgroup & common,
  test.subgroup.random = test.subgroup & random,
  common.subgroup = common,
  random.subgroup = random,
  prediction.subgroup = x$prediction.subgroup,
  print.Q.subgroup = gs("forest.Q.subgroup"),
  label.test.subgroup.common,
  label.test.subgroup.random,
  test.effect.subgroup = gs("test.effect.subgroup"),
  test.effect.subgroup.common,
  test.effect.subgroup.random,
  label.test.effect.subgroup.common,
  label.test.effect.subgroup.random,
  text.addline1,
  text.addline2,
  details = gs("forest.details"),
  col.lines = gs("col.lines"),
  header.line,
  col.header.line = col.lines,
  col.jama.line = col.subgroup,
  fontsize = gs("fontsize"),
  fontfamily = gs("fontfamily"),
  fs.heading = fontsize,
  fs.common = gs("fs.common"),
  fs.random = gs("fs.random"),
  fs.predict = gs("fs.predict"),
  fs.common.labels = gs("fs.common.labels"),
  fs.random.labels = gs("fs.random.labels"),
  fs.predict.labels = gs("fs.predict.labels"),
  fs.study = fontsize,
  fs.study.labels = fs.study,
  fs.hetstat = gs("fs.hetstat"),
  fs.test.overall = gs("fs.test.overall"),
  fs.test.subgroup = gs("fs.test.subgroup"),
  fs.test.effect.subgroup = gs("fs.test.effect.subgroup"),
  fs.addline = gs("fs.addline"),
  fs.axis = fontsize,
  fs.smlab = fontsize,
  fs.xlab = fontsize,
  fs.lr = fontsize,
  fs.rob = fontsize,
  fs.rob.symbols = fontsize,
  fs.details = fontsize,
  ff.heading = "bold",
  ff.common = gs("ff.common"),
  ff.random = gs("ff.random"),
  ff.predict = gs("ff.predict"),
  ff.common.labels = gs("ff.common.labels"),
  ff.random.labels = gs("ff.random.labels"),
  ff.predict.labels = gs("ff.predict.labels"),
  ff.study = "plain",
  ff.study.labels = ff.study,
  ff.hetstat = gs("ff.hetstat"),
  ff.test.overall = gs("ff.test.overall"),
  ff.test.subgroup = gs("ff.test.subgroup"),
  ff.test.effect.subgroup = gs("ff.test.effect.subgroup"),
  ff.addline = gs("ff.addline"),
  ff.axis = gs("ff.axis"),
  ff.smlab = gs("ff.smlab"),
  ff.xlab = gs("ff.xlab"),
  ff.lr = gs("ff.lr"),
  ff.rob = "plain",
  ff.rob.symbols = "bold",
  ff.details = "plain",
  squaresize = if (layout == "BMJ") 0.9/spacing else 0.8/spacing,
  lwd.square = gs("lwd.square"),
  lwd.diamond = gs("lwd.diamond"),
  arrow.type = gs("arrow.type"),
  arrow.length = gs("arrow.length"),
  plotwidth = if (layout %in% c("BMJ", "JAMA")) "8cm" else "6cm",
  colgap = gs("colgap"),
  colgap.left = colgap,
  colgap.right = colgap,
  colgap.studlab = colgap.left,
  colgap.forest = gs("colgap.forest"),
  colgap.forest.left = colgap.forest,
  colgap.forest.right = colgap.forest,
  colgap.rob = "1mm",
  colgap.rob.overall = "2mm",
  calcwidth.pooled = (common | random) & (overall | !is.null(x$subgroup)),
  calcwidth.common = calcwidth.pooled,
  calcwidth.random = calcwidth.pooled,
  calcwidth.predict = gs("calcwidth.predict"),
  calcwidth.hetstat = gs("calcwidth.hetstat"),
  calcwidth.tests = gs("calcwidth.tests"),
  calcwidth.subgroup = gs("calcwidth.subgroup"),
  calcwidth.addline = gs("calcwidth.addline"),
  just = if (layout == "JAMA") "left" else "right",
  just.studlab = gs("just.studlab"),
  just.addcols = gs("just.addcols"),
  just.addcols.left = just.addcols,
  just.addcols.right = just.addcols,
  bmj.text = NULL,
  bmj.xpos = 0,
  bmj.sep = " / ",
  spacing = gs("spacing"),
  addrow = gs("addrow"),
  addrow.overall = gs("addrow.overall"),
  addrow.subgroups = gs("addrow.subgroups"),
  addrows.below.overall = gs("addrows.below.overall"),
  new = TRUE,
  backtransf = x$backtransf,
  digits = gs("digits.forest"),
  digits.se = gs("digits.se"),
  digits.stat = gs("digits.stat"),
  digits.pval = gs("digits.pval"),
  digits.pval.Q = gs("digits.pval.Q"),
  digits.Q = gs("digits.Q"),
  digits.tau2 = gs("digits.tau2"),
  digits.tau = gs("digits.tau"),
  digits.I2 = gs("digits.I2"),
  digits.weight = gs("digits.weight"),
  digits.mean = gs("digits.mean"),
  digits.sd = gs("digits.sd"),
  digits.cor = digits,
  digits.time = digits,
  digits.n = 0,
  digits.event = 0,
  digits.TE = gs("digits.TE.forest"),
  digits.addcols = digits,
  digits.addcols.right = digits.addcols,
  digits.addcols.left = digits.addcols,
  scientific.pval = gs("scientific.pval"),
  big.mark = gs("big.mark"),
  zero.pval = if (layout == "JAMA") FALSE else gs("zero.pval"),
  JAMA.pval = if (layout == "JAMA") TRUE else gs("JAMA.pval"),
  warn.deprecated = gs("warn.deprecated"),
  ...
)

## S3 method for class 'meta'
plot(x, ...)

.forestArgs()

Arguments

x	An object of class meta.
sortvar	An optional vector used to sort the individual studies (must be of same length as x$TE).
studlab	A logical indicating whether study labels should be printed in the graph. A vector with study labels can also be provided (must be of same length as x$TE then).
layout	A character string specifying the layout of the forest plot (see Details).
common	A logical indicating whether common effect estimate should be plotted.
random	A logical indicating whether random effects estimate should be plotted.
overall	A logical indicating whether overall summaries should be plotted. This argument is useful in a meta-analysis with subgroups if summaries should only be plotted on group level.
text.common	A character string used in the plot to label the pooled common effect estimate.
text.random	A character string used in the plot to label the pooled random effects estimate.
lty.common	Line type of pooled common effect estimate.
lty.random	Line type of pooled random effects estimate.
col.common	Line colour of pooled common effect estimate.
col.random	Line colour of pooled random effects estimate.
text.w.common	A character string used to label weights of common effect model.
text.w.random	A character string used to label weights of random effects model.
prediction	A logical indicating whether a prediction interval should be printed.
text.predict	A character string used in the plot to label the prediction interval.
subgroup	A single logical or logical vector indicating whether / which subgroup results should be shown in forest plot. This argument is useful in a meta-analysis with subgroups if summaries should not be plotted for (some) subgroups.
subgroup.hetstat	A single logical or logical vector indicating whether / which information on heterogeneity in subgroups should be shown in forest plot. This argument is useful in a meta-analysis with subgroups if heterogeneity statistics should not be printed for (some) subgroups.
print.subgroup.labels	A logical indicating whether subgroup label should be printed.
subgroup.name	A character string with a label for the grouping variable.
print.subgroup.name	A logical indicating whether the name of the grouping variable should be printed in front of the group labels.
sep.subgroup	A character string defining the separator between label and levels of grouping variable.
text.common.w	A character string to label the pooled common effect estimate within subgroups, or a character vector of same length as number of subgroups with corresponging labels.
text.random.w	A character string to label the pooled random effect estimate within subgroups, or a character vector of same length as number of subgroups with corresponging labels.
text.predict.w	A character string to label the prediction interval within subgroups, or a character vector of same length as number of subgroups with corresponging labels.
sort.subgroup	A logical indicating whether groups should be ordered alphabetically.
pooled.totals	A logical indicating whether total number of observations should be given in the figure.
pooled.events	A logical indicating whether total number of events should be given in the figure.
pooled.times	A logical indicating whether total person time at risk should be given in the figure.
study.results	A logical indicating whether results for individual studies should be shown in the figure (useful to only plot subgroup results).
rob	Risk of bias (RoB) assessment.
rob.text	Column heading for RoB table.
rob.xpos	A numeric specifying the horizontal position of the risk of bias label in RoB table heading. The value is a so called normalised parent coordinate in the horizontal direction (see unit).
rob.legend	A logical specifying whether a legend with RoB domains should be printed.
rob.only	A logical indicating whether the risk of bias assessment is the only information printed on the right side of the forest plot.
xlab	A label for the x-axis.
xlab.pos	A numeric specifying the center of the label on the x-axis.
smlab	A label for the summary measure (printed at top of figure).
smlab.pos	A numeric specifying the center of the label for the summary measure.
xlim	The x limits (min,max) of the plot, or the character string "symmetric" to produce symmetric forest plots.
allstudies	A logical indicating whether studies with inestimable treatment effects should be included in the forest plot.
weight.study	A character string indicating weighting used to determine size of squares or diamonds (argument type.study) to plot individual study results. One of missing, "same", "common", or "random", can be abbreviated. Plot symbols have the same size for all studies or represent study weights from common effect or random effects model.
pscale	A numeric giving scaling factor for printing of single event probabilities or risk differences, i.e. if argument sm is equal to "PLOGIT", "PLN", "PRAW", "PAS", "PFT", or "RD".
irscale	A numeric defining a scaling factor for printing of single incidence rates or incidence rate differences, i.e. if argument sm is equal to "IR", "IRLN", "IRS", "IRFT", or "IRD".
irunit	A character specifying the time unit used to calculate rates, e.g., person-years.
file	File name.
width	Width of graphics file.
rows.gr	Additional rows in forest plot to change height of graphics file (e.g., in order to add a title at the top of the forest plot).
func.gr	Name of graphics function, e.g., pdf.
args.gr	List with additional graphical parameters passed on to graphics function (argument 'height' cannot be provided as the height is calculated internally; use instead argument 'rows.gr').
dev.off	A logical to specify whether current graphics device should be shut down, i.e., whether file should be stored.
ref	A numerical giving the reference value to be plotted as a line in the forest plot. No reference line is plotted if argument ref is equal to NA.
lower.equi	A numerical giving the lower limit of equivalence to be plotted as a line in the forest plot. Or a vector to provide several limits, e.g., for large, moderate and small effects. No line is plotted if argument lower.equi is equal to NA.
upper.equi	A numerical giving the upper limit of equivalence to be plotted as a line in the forest plot. Or a vector to provide several limits, e.g., for small, moderate and large effects. No line is plotted if argument upper.equi is equal to NA.
lty.equi	Line type (limits of equivalence).
col.equi	Line colour (limits of equivalence).
fill.equi	Colour(s) for area between limits of equivalence or more general limits.
fill.lower.equi	Colour of area between lower limit(s) and reference value. Can be equal to the number of lower limits or the number of limits plus 1 (in this case the the region between minimum and smallest limit is also filled).
fill.upper.equi	Colour of area between reference value and upper limit(s). Can be equal to the number of upper limits or the number of limits plus 1 (in this case the region between largest limit and maximum is also filled).
fill	Colour for background of confidence interval plot.
leftcols	A character vector specifying (additional) columns to be printed on the left side of the forest plot or a logical value (see Details).
rightcols	A character vector specifying (additional) columns to be printed on the right side of the forest plot or a logical value (see Details).
leftlabs	A character vector specifying labels for (additional) columns on left side of the forest plot (see Details).
rightlabs	A character vector specifying labels for (additional) columns on right side of the forest plot (see Details).
label.e	Label to be used for experimental group in table heading.
label.c	Label to be used for control group in table heading.
label.e.attach	A character specifying the column name where label label.e should be attached to in table heading.
label.c.attach	A character specifying the column name where label label.c should be attached to in table heading.
label.left	Graph label on left side of null effect.
label.right	Graph label on right side of null effect.
bottom.lr	A logical indicating whether labels on right and left side should be printed at bottom or top of forest plot.
lab.NA	A character string to label missing values.
lab.NA.effect	A character string to label missing values in individual treatment estimates and confidence intervals.
lab.NA.weight	A character string to label missing weights.
lwd	The line width, see par.
at	The points at which tick-marks are to be drawn, see grid.xaxis.
label	A logical value indicating whether to draw the labels on the tick marks, or an expression or character vector which specify the labels to use. See grid.xaxis.
col.label	The colour of labels on the x-axis.
type.study	A character string or vector specifying how to plot treatment effects and confidence intervals for individual studies (see Details).
type.common	A character string specifying how to plot treatment effect and confidence interval for common effect meta-analysis (see Details).
type.random	A character string specifying how to plot treatment effect and confidence interval for random effects meta-analysis (see Details).
type.subgroup	A character string specifying how to plot treatment effect and confidence interval for subgroup results (see Details).
type.subgroup.common	A character string specifying how to plot treatment effect and confidence interval for subgroup results (common effect model).
type.subgroup.random	A character string specifying how to plot treatment effect and confidence interval for subgroup results (random effects model).
col.study	The colour for individual study results and confidence limits.
col.square	The colour for squares reflecting study's weight in the meta-analysis.
col.square.lines	The colour for the outer lines of squares reflecting study's weight in the meta-analysis.
col.circle	The colour for circles reflecting study weights in the meta-analysis.
col.circle.lines	The colour for the outer lines of circles reflecting study's weight in the meta-analysis.
col.inside	The colour for individual study results and confidence limits if confidence limits are completely within squares.
col.inside.common	The colour for result of common effect meta-analysis if confidence limit lies completely within square.
col.inside.random	The colour for result of random effects meta-analysis if confidence limit lies completely within square.
col.diamond	The colour of diamonds representing the results for common effect and random effects models.
col.diamond.common	The colour(s) of diamonds for common effect estimates.
col.diamond.random	The colour(s) of diamonds for random effects estimates.
col.diamond.lines	The colour of the outer lines of diamonds representing the results for common effect and random effects models.
col.diamond.lines.common	The colour(s) of the outer lines of diamond for common effect estimate.
col.diamond.lines.random	The colour(s) of the outer lines of diamond for random effects estimate.
col.predict	Background colour(s) of prediction intervals.
col.predict.lines	Colour(s) of outer lines of prediction intervals.
col.subgroup	The colour to print information on subgroups.
col.label.left	The colour of the label on the left side of the null effect.
col.label.right	The colour of the label on the right side of the null effect.
hetstat	Either a logical value indicating whether to print results for heterogeneity measures at all or a character string (see Details).
overall.hetstat	A logical value indicating whether to print heterogeneity measures for overall treatment comparisons. This argument is useful in a meta-analysis with subgroups if heterogeneity statistics should only be printed on subgroup level.
hetlab	Label printed in front of results for heterogeneity measures.
resid.hetstat	A logical value indicating whether to print measures of residual heterogeneity in a meta-analysis with subgroups.
resid.hetlab	Label printed in front of results for residual heterogeneity measures.
print.I2	A logical value indicating whether to print the value of the I-squared statistic.
print.I2.ci	A logical value indicating whether to print the confidence interval of the I-squared statistic.
print.tau2	A logical value indicating whether to print the value of the between-study variance $\tau^2$.
print.tau2.ci	A logical value indicating whether to print the confidence interval of $\tau^2$.
print.tau	A logical value indicating whether to print $\tau$, the square root of the between-study variance $\tau^2$.
print.tau.ci	A logical value indicating whether to print the confidence interval of $\tau$.
print.Q	A logical value indicating whether to print the value of the heterogeneity statistic Q.
print.pval.Q	A logical value indicating whether to print the p-value of the heterogeneity statistic Q.
print.Rb	A logical value indicating whether to print the value of the I-squared statistic.
print.Rb.ci	A logical value indicating whether to print the confidence interval of the I-squared statistic.
text.subgroup.nohet	A logical value or character string which is printed to indicate subgroups with less than two studies contributing to meta-analysis (and thus without heterogeneity). If FALSE, heterogeneity statistics are printed (with NAs).
LRT	A logical value indicating whether to report Likelihood-Ratio or Wald-type test of heterogeneity for generalised linear mixed models.
test.overall	A logical value indicating whether to print results of test for overall effect.
test.overall.common	A logical value indicating whether to print results of test for overall effect (common effect model).
test.overall.random	A logical value indicating whether to print results of test for overall effect (random effects model).
label.test.overall.common	Label printed in front of results of test for overall effect (common effect model).
label.test.overall.random	Label printed in front of results of test for overall effect (random effects model).
print.stat	A logical value indicating whether z- or t-value for test of treatment effect should be printed.
test.subgroup	A logical value indicating whether to print results of test for subgroup differences.
test.subgroup.common	A logical value indicating whether to print results of test for subgroup differences (common effect model).
test.subgroup.random	A logical value indicating whether to print results of test for subgroup differences (random effects model).
common.subgroup	A single logical or logical vector indicating whether / which common effect estimates should be printed for subgroups.
random.subgroup	A single logical or logical vector indicating whether / which random effects estimates should be printed for subgroups.
prediction.subgroup	A single logical or logical vector indicating whether / which prediction intervals should be printed for subgroups.
print.Q.subgroup	A logical value indicating whether to print the value of the heterogeneity statistic Q (test for subgroup differences).
label.test.subgroup.common	Label printed in front of results of test for subgroup differences (common effect model).
label.test.subgroup.random	Label printed in front of results of test for subgroup differences (random effects model).
test.effect.subgroup	A single logical or logical vector indicating whether / which tests for effect in subgroups should be printed.
test.effect.subgroup.common	A single logical or logical vector indicating whether / which tests for effect in subgroups should be printed (common effect model).
test.effect.subgroup.random	A single logical or logical vector indicating whether / which tests for effect in subgroups should be printed (random effects model).
label.test.effect.subgroup.common	Label printed in front of results of test for effect in subgroups (common effect model).
label.test.effect.subgroup.random	Label printed in front of results of test for effect in subgroups (random effects model).
text.addline1	Text for first additional line (below meta-analysis results).
text.addline2	Text for second additional line (below meta-analysis results).
details	A logical specifying whether details on statistical methods should be printed.
col.lines	The colour of lines.
header.line	A logical value indicating whether to print a header line or a character string ("both", "below", "").
col.header.line	Colour of the header line(s).
col.jama.line	Colour of the additional JAMA lines.
fontsize	The size of text (in points), see gpar.
fontfamily	The font family, see gpar.
fs.heading	The size of text for column headings, see gpar.
fs.common	The size of text for results of common effect model, see gpar.
fs.random	The size of text for results of random effects model, see gpar.
fs.predict	The size of text for results of prediction interval, see gpar.
fs.common.labels	The size of text for label of common effect model, see gpar.
fs.random.labels	The size of text for label of random effects model, see gpar.
fs.predict.labels	The size of text for label of prediction interval, see gpar.
fs.study	The size of text for results of individual studies, see gpar.
fs.study.labels	The size of text for labels of individual studies, see gpar.
fs.hetstat	The size of text for heterogeneity measures, see gpar.
fs.test.overall	The size of text of test for overall effect, see gpar.
fs.test.subgroup	The size of text of test of subgroup differences, see gpar.
fs.test.effect.subgroup	The size of text of test of effect in subgroups, see gpar.
fs.addline	The size of text for additional lines, see gpar.
fs.axis	The size of text on x-axis, see gpar.
fs.smlab	The size of text of label for summary measure, see gpar.
fs.xlab	The size of text of label on x-axis, see gpar.
fs.lr	The size of text of label on left and right side of forest plot, see gpar.
fs.rob	The size of text of risk of bias items in the legend, see gpar.
fs.rob.symbols	The size of risk of bias symbols, see gpar.
fs.details	The size of text for details on (meta-analysis) methods, see gpar.
ff.heading	The fontface for column headings, see gpar.
ff.common	The fontface of text for results of common effect model, see gpar.
ff.random	The fontface of text for results of random effects model, see gpar.
ff.predict	The fontface of text for results of prediction interval, see gpar.
ff.common.labels	The fontface of text for label of common effect model, see gpar.
ff.random.labels	The fontface of text for label of random effects model, see gpar.
ff.predict.labels	The fontface of text for label of prediction interval, see gpar.
ff.study	The fontface of text for results of individual studies, see gpar.
ff.study.labels	The fontface of text for labels of individual studies, see gpar.
ff.hetstat	The fontface of text for heterogeneity measures, see gpar.
ff.test.overall	The fontface of text of test for overall effect, see gpar.
ff.test.subgroup	The fontface of text for test of subgroup differences, see gpar.
ff.test.effect.subgroup	The fontface of text for test of effect in subgroups, see gpar.
ff.addline	The fontface of text for additional lines, see gpar.
ff.axis	The fontface of text on x-axis, see gpar.
ff.smlab	The fontface of text of label for summary measure, see gpar.
ff.xlab	The fontface of text of label on x-axis, see gpar.
ff.lr	The fontface of text of label on left and right side of forest plot, see gpar.
ff.rob	The fontface of text of risk of bias items, see gpar.
ff.rob.symbols	The fontface of risk of bias symbols, see gpar.
ff.details	The fontface for details on (meta-analysis) methods, see gpar.
squaresize	A numeric used to increase or decrease the size of squares in the forest plot.
lwd.square	The line width of the border around squares.
lwd.diamond	The line width of the border around diamonds.
arrow.type	A character string indicating whether arrows printed for results outside the forest plot should be "open", or "closed", can be abbreviated.
arrow.length	The length of arrows in inches.
plotwidth	Either a character string, e.g., "8cm", "60mm", or "3inch", or a unit object specifying width of the forest plot.
colgap	Either a character string or a unit object specifying gap between columns printed on left and right side of forest plot.
colgap.left	Either a character string or a unit object specifying gap between columns printed on left side of forest plot.
colgap.right	Either a character string or a unit object specifying gap between columns printed on right side of forest plot.
colgap.studlab	Either a character string or a unit object specifying gap between column with study labels and subsequent column.
colgap.forest	Either a character string or a unit object specifying gap between column adjacent to forest plot and the forest plot.
colgap.forest.left	Either a character string or a unit object specifying gap between column on the left side of forest plot and the forest plot.
colgap.forest.right	Either a character string or a unit object specifying gap between column on the right side of forest plot and the forest plot.
colgap.rob	Either a character string or a unit object specifying gap between risk of bias columns.
colgap.rob.overall	Either a character string or a unit object specifying gap before column with overall risk of bias assessment.
calcwidth.pooled	A logical indicating whether text for common effect and random effects model should be considered to calculate width of the column with study labels.
calcwidth.common	A logical indicating whether text given in arguments text.common and text.common.w should be considered to calculate width of the column with study labels.
calcwidth.random	A logical indicating whether text given in arguments text.random and text.random.w should be considered to calculate width of the column with study labels.
calcwidth.predict	A logical indicating whether text given in argument text.predict and text.predict.w should be considered to calculate width of the column with study labels.
calcwidth.hetstat	A logical indicating whether text for heterogeneity statistics should be considered to calculate width of the column with study labels.
calcwidth.tests	A logical indicating whether text for tests of overall effect or subgroup differences should be considered to calculate width of the column with study labels.
calcwidth.subgroup	A logical indicating whether text with subgroup labels should be considered to calculate width of the column with study labels.
calcwidth.addline	A logical indicating whether text for additional lines should be considered to calculate width of the column with study labels.
just	Justification of text in all columns but columns with study labels and additional variables (possible values: "left", "right", "center").
just.studlab	Justification of text for study labels (possible values: "left", "right", "center").
just.addcols	Justification of text for additional columns (possible values: "left", "right", "center").
just.addcols.left	Justification of text for additional columns on left side of forest plot (possible values: "left", "right", "center"). Can be of same length as number of additional columns on left side of forest plot.
just.addcols.right	Justification of text for additional columns on right side of forest plot (possible values: "left", "right", "center"). Can be of same length as number of additional columns on right side of forest plot.
bmj.text	A character string used in the plot with BMJ layout to label the group specific information.
bmj.xpos	A numeric specifying the horizontal position of the BMJ label. The value is a so called normalised parent coordinate in the horizontal direction (see unit).
bmj.sep	A character string used to separate sample sizes from number of events or means / standard deviations.
spacing	A numeric determining line spacing in a forest plot.
addrow	A logical value indicating whether an empty row is printed above study results.
addrow.overall	A logical value indicating whether an empty row is printed above overall meta-analysis results.
addrow.subgroups	A logical value indicating whether an empty row is printed between results for subgroups.
addrows.below.overall	A numeric value indicating how many empty rows are printed between meta-analysis results and heterogeneity statistics and test results.
new	A logical value indicating whether a new figure should be printed in an existing graphics window.
backtransf	A logical indicating whether results should be back transformed in forest plots. If backtransf = TRUE, results for sm = "OR" are presented as odds ratios rather than log odds ratios and results for sm = "ZCOR" are presented as correlations rather than Fisher's z transformed correlations, for example.
digits	Minimal number of significant digits for treatment effects, see print.default.
digits.se	Minimal number of significant digits for standard errors.
digits.stat	Minimal number of significant digits for z- or t-statistic for test of overall effect.
digits.pval	Minimal number of significant digits for p-value of overall treatment effect.
digits.pval.Q	Minimal number of significant digits for p-value of heterogeneity test.
digits.Q	Minimal number of significant digits for heterogeneity statistic Q.
digits.tau2	Minimal number of significant digits for between-study variance.
digits.tau	Minimal number of significant digits for square root of between-study variance.
digits.I2	Minimal number of significant digits for I-squared statistic.
digits.weight	Minimal number of significant digits for weights.
digits.mean	Minimal number of significant digits for means; only applies to metacont objects.
digits.sd	Minimal number of significant digits for standard deviations; only applies to metacont objects.
digits.cor	Minimal number of significant digits for correlations; only applies to metacor objects.
digits.time	Minimal number of significant digits for times; only applies to metainc and metarate objects.
digits.n	Minimal number of significant digits for sample sizes.
digits.event	Minimal number of significant digits for event numbers.
digits.TE	Minimal number of significant digits for list element 'TE'.
digits.addcols	A vector or scalar with minimal number of significant digits for additional columns.
digits.addcols.right	A vector or scalar with minimal number of significant digits for additional columns on right side of forest plot.
digits.addcols.left	A vector or scalar with minimal number of significant digits for additional columns on left side of forest plot.
scientific.pval	A logical specifying whether p-values should be printed in scientific notation, e.g., 1.2345e-01 instead of 0.12345.
big.mark	A character used as thousands separator.
zero.pval	A logical specifying whether p-values should be printed with a leading zero.
JAMA.pval	A logical specifying whether p-values for test of overall effect should be printed according to JAMA reporting standards.
warn.deprecated	A logical indicating whether warnings should be printed if deprecated arguments are used.
...	Additional graphical arguments.

Details

A forest plot, also called confidence interval plot, is drawn in the active graphics window. The forest functions in R package meta are based on the grid graphics system. Resize the graphics windows if the forest plot is too large or too small for the graphics window. Alternatively, save the forest plot in a file.

Saving forest plots

A forest plot can be directly stored in a file using argument file or specifying the R function for the graphics device driver using argument func.gr, e.g., pdf. If only the filename is provided, the extension is checked and matched against the most common graphics device drivers.

Extension	Graphics device
.pdf	pdf
.ps	postscript
.svg	svg
.bmp	bmp
.jpg / .jpeg	jpeg
.png	png
.tif / .tiff	tiff

The height of the graphics device is automatically determined if the forest plot is saved to a file. Argument rows.gr can be used to increase or decrease the number of rows shown in the forest plot (either to show missing information or to remove whitespace). The width of the graphics device can be specified with argument width, see, for example, pdf or jpeg. Other arguments of graphics device functions can be provided as a list in argument args.gr.

Alternatively, the (resized) graphics window can be stored to a file using either dev.copy2eps or dev.copy2pdf. It is also possible to manually create a file using, for example, pdf, png, or svg and to specify the width and height of the graphic (see Examples).

Default layout for studies and pooled effects

By default, treatment estimates and confidence intervals are plotted in the following way:

• For an individual study, a square with treatment estimate in the center and confidence interval as line extending either side of the square (type.study = "square")

• For meta-analysis results, a diamond with treatment estimate in the center and right and left side corresponding to lower and upper confidence limits (type.common = "diamond", type.random = "diamond", and type.subgroup = "diamond")

In a forest plot, size of the squares typically reflects the precision of individual treatment estimates based either on the common effect (weight.study = "common") or random effects meta-analysis (weight.study = "random"). Information from meta-analysis object x is utilised if argument weight.study is missing. Weights from the common effect model are used if argument x$common is TRUE; weights from the random effects model are used if argument x$random is TRUE and x$common is FALSE. The same square sizes are used if weight.study = "same".

A prediction interval for treatment effect of a new study (Higgins et al., 2009) is given in the forest plot if arguments prediction and random are TRUE. For graphical presentation of prediction intervals the approach by Guddat et al. (2012) is used.

Columns printed on left side of forest plot

Argument leftcols can be used to specify columns which are printed on the left side of the forest plot. By default, i.e. if argument leftcols is NULL and layout = "meta", and depending on the class of the meta-analysis object (which is defined by the R function used to generate the object) a different set of columns is printed on the left side of the forest plot:

Function	Value of argument leftcols
metabin	c("studlab", "event.e", "n.e", "event.c", "n.c")
metacont	c("studlab", "n.e", "mean.e", "sd.e", "n.c", "mean.c", "sd.c")
metacor	c("studlab", "n")
metagen	c("studlab", "TE", "seTE")
metainc	c("studlab", "event.e", "time.e", "event.c", "time.c")
metamean	c("studlab", "n", "mean", "sd")
metaprop	c("studlab", "event", "n")
metarate	c("studlab", "event", "time", "n")
metacum	"studlab"
metainf	"studlab"

For three-level models, the cluster variable is printed next to the study labels (value "cluster" in argument leftcols).

By default, study labels and labels for pooled estimates and heterogeneity statistics will be printed in the first column on the left side of the forest plot. The character string "studlab" is used to identify study labels as this is the name of the list element of a meta-analysis object.

If the character string "studlab" is not provided in leftcols and rightcols, the first additional variable specified by the user is used as study labels (and labels for pooled estimates are printed in this column). Additional variables are any variables not mentioned in the section on predefined column names below. For example, leftcols = "studlab" and leftcols = "study" would result in the same forest plot if the variable "study" was used in the command to conduct the meta-analysis. If no additional variable is provided by the user, no study labels will be printed.

Overlapping information on left side of forest plot

Depending on the number of columns printed on the left side of the forest plot, information on heterogeneity measures or statistical tests (see below) can be overlapping with the x-axis. Argument addrows.below.overall can be used to specify the number of empty rows that are printed between meta-analysis results and information on heterogeneity measures and statistical tests. By default, no additional rows are added to the forest plot. If addrows.below.overall = NULL, the function tries to add a sufficient number of empty rows to prevent overlapping text. Another possibility is to manually increase the space between the columns on the left side (argument colgap.left) or between the columns on the left side and the forest plot (argument colgap.forest.left).

Columns printed on right side of forest plot

Argument rightcols can be used to specify columns which are printed on the right side of the forest plot. If argument rightcols is FALSE, no columns will be printed on the right side. By default, i.e. if argument rightcols is NULL and layout = "meta", the following columns will be printed on the right side of the forest plot:

Meta-analysis results	Value of argument rightcols
No summary	c("effect", "ci")
Only common effect model	c("effect", "ci", "w.common")
Only random effects model	c("effect", "ci", "w.random")
Both models	c("effect", "ci", "w.common", "w.random")

By default, estimated treatment effect and corresponding confidence interval will be printed. Depending on arguments common and random, weights of the common effect and/or random effects model will be given too.

For an object of class metacum or metainf the following columns will be printed: c("effect", "ci", "pval", "tau2", "tau", "I2"). This information corresponds to the printout with print.meta.

Predefined column names

The arguments leftlabs and rightlabs can be used to specify column headings which are printed on left or right side of the forest plot. For certain columns predefined labels exist which are used by default, i.e., if arguments leftlabs and rightlabs are NULL:

Column:	studlab	TE	seTE	cluster	n.e	n.c
Label:	"Study"	"TE"	"seTE"	"Cluster"	"Total"	"Total"
Column:	n	event.e	event.c	event	mean.e	mean.c
Label:	"Total"	"Events"	"Events"	"Events"	"Mean"	"Mean"
Column:	sd.e	sd.c	time.e	time.c	effect
Label:	"SD"	"SD"	"Time"	"Time"	x$sm
Column:	ci	effect.ci	w.common	w.random	cycles
Label:	x$level"%-CI"	effect+ci	"W(common)"	"W(random)"	"Cycles"

For other columns, the column name will be used as a label if no column label is defined. It is possible to only provide labels for new columns (see Examples). Otherwise the length of leftlabs and rightlabs must be the same as the number of printed columns. The value NA can be used to specify columns which should use default labels (see Examples).

In pairwise meta-analysis comparing two groups (i.e., metabin, metacont, metainc, and metagen depending on the outcome), arguments label.e and label.c are used to label columns belonging to the two treatment groups. By default, labels defined in the meta-analysis object are used. The columns where treatment labels are attached can be changed using arguments label.e.attach and label.c.attach.

Risk of bias assessment

A risk of bias (RoB) assessment can be shown in the forest plot by either using a meta-analysis object with an RoB assessment as main input or providing a suitable object created with rob. Argument rob = FALSE can be used to suppress the print of the risk of bias information.

RoB assessments are shown as the only information on the right side of the forest plot. Thus, arguments rightcols and rightlabs should not be used. Predefined columns shown by default on the right side of a forest plot will be moved to the left side.

Information on heterogeneity and statistical tests

Argument hetstat can be a character string to specify where to print heterogeneity information:

• row with results for common effect model (hetstat = "common"),

• row with results for random effects model (hetstat = "random").

Otherwise, information on heterogeneity measures is printed below the meta-analysis results if argument overall.hetstat = TRUE (default). The heterogeneity measures to print can be specified (see list of arguments following overall.hetstat).

In addition, the following arguments can be used to print results for various statistical tests:

Argument	Statistical test
test.overall.common	Test for overall effect (common effect model)
test.overall.random	Test for overall effect (random effects model)
test.effect.subgroup.common	Test for effect in subgroup (CE model)
test.effect.subgroup.random	Test for effect in subgroup (RE model)
test.subgroup.common	Test for subgroup differences (CE model)
test.subgroup.random	Test for subgroup differences (RE model)

By default, these arguments are FALSE with exception of tests for subgroup differences which are TRUE. R function settings.meta can be used to change this default for the entire R session. For example, use the following command to always print results of tests for an overall effect: settings.meta(test.overall = TRUE).

Flexible printing of subgroup results

Argument subgroup determines whether summary results are printed for subgroups. A logical vector of length equal to the number of subgroups can be provided to determine which subgroup summaries are printed. By default, only subgroup results based on at least two studies are printed which is identical to use argument subgroup = k.w > 1. The order of the logical vector corresponds to the order of subgroups in list element 'subgroup.levels' of a meta-analysis object. Argument subgroup = k.w >= 1 can be used to show results for all subgroups (including those with a single study).

The following arguments can be used in a similar way:

• subgroup.hetstat (heterogeneity statistic in subgroups),

• common.subgroup (common effect estimates in subgroups),

• random.subgroup (random effects estimates in subgroups),

• prediction.subgroup (prediction interval in subgroups),

• test.effect.subgroup (test for effect in subgroups),

• test.effect.subgroup.common (test for effect in subgroups, common effect model),

• test.effect.subgroup.random (test for effect in subgroups, random effects model).

Additional general settings

Arguments text.common, text.random, and text.predict can be used to change the label to identify overall results (common effect and random effects model as well as prediction interval). By default the following text is printed:

• "Common effect model" (argument text.common)

• "Random effects model" (text.random)

• "Prediction interval" (text.predict)

If confidence interval levels are different for individual studies, meta-analysis, and prediction interval (arguments level, level.ma, level.predict in meta-analysis functions, e.g., metabin), additional information is printed, e.g., " (99%-CI)" for a 99% confidence interval in the meta-analysis.

Argument pscale can be used to rescale single proportions or risk differences, e.g., pscale = 1000 means that proportions are expressed as events per 1000 observations. This is useful in situations with (very) low event probabilities.

Argument irscale can be used to rescale single rates or rate differences, e.g., irscale = 1000 means that rates are expressed as events per 1000 time units, e.g., person-years. This is useful in situations with (very) low rates. Argument irunit can be used to specify the time unit used in individual studies (default: "person-years"). This information is printed in summaries and forest plots if argument irscale is not equal to 1.

Forest plots in RevMan5 layout

If argument layout = "RevMan5" (and arguments leftcols and rightcols are NULL), the layout for forest plots used for Cochrane reviews (which were generated with Review Manager 5) is reproduced:

1. All columns are printed on the left side of the forest plot (see arguments leftcols and rightcols)

2. Tests for overall effect and subgroup differences are printed (test.overall, test.effect.subgroup, test.subgroup)

3. Diamonds representing meta-analysis results are printed in black (diamond.common, diamond.random)

4. Colour of squares depends on the meta-analysis object (col.square, col.square.lines)

5. Information on effect measure and meta-analysis method is printed above the forest plot (smlab)

6. Label "Study or Subgroup" is printed for meta-analysis with subgroups (leftlabs)

Forest plots in JAMA layout

If argument layout = "JAMA" (and arguments leftcols and rightcols are NULL), instructions for authors of the Journal of the American Medical Association, see https://jamanetwork.com/journals/jama/pages/instructions-for-authors/, are taken into account:

1. Graph labels on right and left side are printed in bold font at top of forest plot (see arguments bottom.lr and ff.lr)

2. Information on effect measure and level of confidence interval is printed at bottom of forest plot (xlab)

3. Tests for overall effect are printed (test.overall)

4. Diamonds representing meta-analysis results are printed in lightblue (diamond.common, diamond.random)

5. Squares representing individual study results are printed in darkblue (col.square, col.square.lines)

6. Between-study variance $\tau^2$ is not printed

7. Empty rows are omitted (addrow, addrow.overall, addrow.subgroups)

8. Label "Source" is printed instead of "Study" (leftlabs)

9. P-values are printed without leading zeros (zero.pval)

10. P-values are rounded to three digits (for 0.001 < p $\le$ 0.01) or two digits (p > 0.01) (JAMA.pval)

Study labels according to JAMA guidelines can be generated using labels.meta.

Forest plots showing results of subgroups

The following changes are conducted if argument layout = "subgroup" (and arguments leftcols and rightcols are NULL) and a subgroup analysis was conducted:

1. Individual study results are omitted (see argument study.results)

2. Total number of observations is not printed (pooled.totals)

3. Label "Subgroup" is printed instead of "Study" (leftlabs)

Note

R function .forestArgs generates a character vector with all arguments of forest.meta.

Author(s)

Guido Schwarzer [email protected]

References

Guddat C, Grouven U, Bender R, Skipka G (2012): A note on the graphical presentation of prediction intervals in random-effects meta-analyses. Systematic Reviews, 1, 34

Higgins JPT, Thompson SG, Spiegelhalter DJ (2009): A re-evaluation of random-effects meta-analysis. Journal of the Royal Statistical Society: Series A, 172, 137-59

See Also

metabin, metacont, metagen, forest.metabind, settings.meta, labels.meta

Examples

data(Olkin1995)
m1 <- metabin(ev.exp, n.exp, ev.cont, n.cont,
  data = Olkin1995, subset = c(41, 47, 51, 59),
  sm = "RR", method = "I",
  studlab = paste(author, year))


## Not run: 
# Do standard (symmetric) forest plot
#
forest(m1)

## End(Not run)

# Layout of forest plot similar to Review Manager 5
#
# Furthermore, add labels on both sides of forest plot and
# prediction interval
#
forest(m1, layout = "RevMan5", common = FALSE,
  label.left = "Favours experimental", col.label.left = "green",
  label.right = "Favours control", col.label.right = "red",
  prediction = TRUE)


## Not run: 
# Create PDF files with the forest plot
#
# - specify filename (R function pdf() is used due to extension .pdf)
# - height of the figure is automatically determined
# - width is set to 10 inches
forest(m1, file = "forest-m1-1.pdf", width = 10)
#
# - specify graphics device function
#   (filename "Rplots.pdf" used, see help page of R function pdf())
# - height of the figure is automatically determined
# - width is set to 10 inches
# - set title for PDF file
# - set background of forest plot
forest(m1, func.gr = pdf, width = 10,
  args.gr = list(title = "My Forest Plot", bg = "green"))
#
# - manually specify the height of the figure
pdf("forest-m1-2.pdf", width = 10, height = 3)
forest(m1)
dev.off()

# Define equivalence limits: 0.75 and 1 / 0.75
#
forest(m1, layout = "RevMan5", common = FALSE,
  lower.equi = 0.75, upper.equi = 1 / 0.75, fill.equi = "lightgray")

# Fill areas with beneficial and detrimental effects
#
forest(m1, layout = "RevMan5", common = FALSE,
  lower.equi = 0.75, upper.equi = 1 / 0.75,
  fill.lower.equi = c("green", "lightgray"),
  fill.upper.equi = c("lightgray", "red"))

# Define thresholds for small, moderate and large effects
# and use hcl.colors() to define colours to fill areas
#
thresholds <- c(0.25, 0.5, 0.75)
n.cols <- length(thresholds) + 1
forest(m1, layout = "RevMan5", common = FALSE,
  label.left = "Desirable effect", 
  label.right = "Undesirable effect", 
  lty.equi = 3, col.equi = "darkgray",
  lower.equi = thresholds, upper.equi = 1 / rev(thresholds),
  fill.lower.equi =
    hcl.colors(n.cols, palette = "Blues 2", alpha = 0.6),
  fill.upper.equi =
    hcl.colors(n.cols, palette = "Oranges", alpha = 0.6, rev = TRUE))

# Conduct subgroup meta-analysis
#
m2 <- update(m1,
  subgroup = ifelse(year < 1987, "Before 1987", "1987 and later"),
  print.subgroup.name = FALSE)

# Show summary results for subgroups with at least two studies
#
forest(m2, sortvar = -TE, random = FALSE)

# Show results for all subgroups
#
forest(m2, sortvar = -TE, random = FALSE, subgroup = k.w >= 1)

# Forest plot specifying argument xlim
#
forest(m1, xlim = c(0.01, 10))

# Print results of test for overall effect
#
forest(m1, test.overall.common = TRUE, test.overall.random = TRUE)

# Forest plot with 'classic' layout used in R package meta,
# version < 1.6-0
#
forest(m1, col.square = "black", hetstat = FALSE)

# Change set of columns printed on left side of forest plot
# (resulting in overlapping text)
#
forest(m1, random = FALSE, leftcols = "studlab")

# Use argument 'calcwidth.hetstat' to consider text for heterogeneity
# measures in width of column with study labels
#
forest(m1, random = FALSE, leftcols = "studlab",
  calcwidth.hetstat = TRUE)

# Use argument 'addrows.below.overall' to manually add two empty
# rows
#
forest(m1, random = FALSE, leftcols = "studlab", addrows = 2)

# Do not print columns on right side of forest plot
#
forest(m1, rightcols = FALSE)

# Change study label to "Author"
#
forest(m1, random = FALSE, leftlabs = c("Author", NA, NA, NA, NA))

# Just give effect estimate and 95% confidence interval on right
# side of forest plot (in one column)
#
forest(m1, rightcols = "effect.ci")

# Just give effect estimate and 95% confidence interval on right
# side of forest plot
#
forest(m1, rightcols = c("effect", "ci"))

# 1. Change order of columns on left side
# 2. Attach labels to columns 'event.e' and 'event.c' instead of
#    columns 'n.e' and 'n.c'
#
forest(m1,
  leftcols = c("studlab", "n.e", "event.e", "n.c", "event.c"),
  label.e.attach = "event.e", label.c.attach = "event.c")

# Specify column labels only for variables 'year' and 'author'
# (and define digits for additional variables)
#
forest(m1,
  leftcols = c("studlab", "event.e", "n.e", "event.c", "n.c", "author", "year"),
  leftlabs = c("Author", "Year of Publ"))

# Center text in all columns
#
forest(m1,
  leftcols = c("studlab", "event.e", "n.e", "event.c", "n.c",
               "author", "year"),
  leftlabs = c("Author", "Year of Publ"), hetstat = FALSE,
  just = "center", just.addcols = "center", just.studlab = "center")

# Same result
#
forest(m1,
  leftcols = c("studlab", "event.e", "n.e", "event.c", "n.c",
             "author", "year"),
  leftlabs = c("Author", "Year of Publ"), hetstat = FALSE,
  just = "c", just.addcols = "c", just.studlab = "c")

# Change some fontsizes and fontfaces
#
forest(m1,
  fs.study = 10, ff.study = "italic",
  fs.study.label = 11, ff.study.label = "bold",
  fs.axis = 5, ff.axis = "italic",
  ff.smlab = "bold.italic",
  ff.common = "plain", ff.hetstat = "plain")

# Change some colours
#
forest(m1,
  col.diamond = "green", col.diamond.lines = "red",
  col.study = c("green", "blue", "red", "orange"),
  col.square = "pink", col.square.lines = "black")

# Sort by weight in common effect model
#
forest(m1, sortvar = w.common, random = FALSE)

# Sort by decreasing weight in common effect model
#
forest(m1, sortvar = -w.common, random = FALSE)

# Sort by size of treatment effect
#
forest(m1, sortvar = TE, random = FALSE)

# Sort by size of treatment effect
#
forest(m1, sortvar = -TE, random = FALSE)

# Sort by decreasing year of publication
#
forest(m1, sortvar = -year, random = FALSE)

# Print results of test for subgroup differences (random effects
# model)
#
forest(m2, sortvar = -TE, common = FALSE)

# Print only subgroup results
#
forest(m2, layout = "subgroup")

# Print only subgroup results (and consider text for tests of
# subgroup differences in width of subgroup column)
#
forest(m2, layout = "subgroup", calcwidth.tests = TRUE)

# Print only subgroup results (and consider text for heterogeneity
# in width of subgroup column)
#
forest(m2, layout = "subgroup", calcwidth.hetstat = TRUE)

## End(Not run)

---