metabin(event.e, n.e, event.c, n.c, studlab,
data=NULL, subset=NULL,
method=ifelse(tau.common, "Inverse", "MH"),
sm=ifelse(!is.na(charmatch(method, c("Peto", "peto"),
nomatch=NA)), "OR", "RR"),
incr=0.5, allincr=FALSE, addincr=FALSE, allstudies=FALSE,
MH.exact=FALSE, RR.cochrane=FALSE,
level=0.95, level.comb=level,
comb.fixed=TRUE, comb.random=TRUE,
hakn=FALSE,
method.tau="DL", tau.preset=NULL, TE.tau=NULL,
tau.common=FALSE,
prediction=FALSE, level.predict=level,
method.bias=NULL,
title="", complab="", outclab="",
label.e="Experimental", label.c="Control",
label.left="", label.right="",
byvar, bylab, print.byvar=TRUE,
print.CMH=FALSE, keepdata=TRUE, warn=TRUE)"Inverse", "MH", or
"Peto", can be abbreviated."RR", "OR", "RD", or "AS") is to be used
for pooling of studies, see Details."TA" which stands for treatment arm continuity correction, see
Details.incr is added to each
cell frequency of all studies if at least one study has a zero cell
count. If FALSE (default), incr is added only to each cell frequency of
studies with a zero cell count.incr is added to each cell
frequency of all studies irrespective of zero cell counts.sm is equal to "RR" or "OR").incr is not to be added
to all cell frequencies for studies with a zero cell count to
calculate the pooled estimate based on the Mantel-Haenszel method.incr instead of
1*incr is to be added to n.e and n.c in the
calculation of the risk ratio (i.e., sm="RR") for studies
with a zero cell. This is used in "DL", "REML", "ML", "HS", "SJ",
"HE", or "EB""rank",
"linreg", "mm", "count", "score", or
"peters", can be abbreviated.event.e).incr is added to studies with zero cell
frequencies).c("metabin", "meta") with corresponding
print, summary, plot function. The object is a
list containing the following components:hakn=TRUE).keepdata=TRUE).keepdata=TRUE).sm="RR")sm="OR")sm="RD")sm="AS") For studies with a zero cell count, by default, 0.5 is added to
all cell frequencies of these studies; if incr is
"TA" a treatment arm continuity correction is used instead
(Sweeting et al., 2004; Diamond et al., 2007). Treatment estimates
and standard errors are only calculated for studies with zero or all
events in both groups if allstudies is TRUE.
Internally, both fixed effect and random effects models are calculated
regardless of values choosen for arguments comb.fixed and
comb.random. Accordingly, the estimate for the random effects
model can be extracted from component TE.random of an object
of class "meta" even if comb.random=FALSE. However, all
functions in R package meta will adequately consider the values
for comb.fixed and comb.random. E.g. function
print.meta will not print results for the random effects
model if comb.random=FALSE.
By default, both fixed effect and random effects models are
considered (arguments comb.fixed=TRUE and
comb.random=TRUE). If method is "MH" (default),
the Mantel-Haenszel method is used to calculate the fixed effect
estimate; if method is "Inverse", inverse variance
weighting is used for pooling; finally, if method is
"Peto", the Peto method is used for pooling. By default, the
DerSimonian-Laird estimate is used in the random effects model (see
paragraph on argument method.tau). For the Peto method,
Peto's log odds ratio, i.e. (O-E)/V and its standard error
sqrt(1/V) with O-E and V denoting "Observed
minus Expected" and "V", are utilised in the random effects
model. Accordingly, results of a random effects model using
sm="Peto" can be (slightly) different to results from a
random effects model using sm="MH" or sm="Inverse".
For the Mantel-Haenszel method, by default (if MH.exact is
FALSE), 0.5 is added to all cell frequencies of a study with a zero cell
count in the calculation of the pooled risk ratio or odds ratio as
well as the estimation of the variance of the pooled risk difference,
risk ratio or odds ratio. This approach is also used in other
software, e.g. RevMan 5 and the Stata procedure metan. According to
Fleiss (in Cooper & Hedges, 1994), there is no need to add 0.5 to a
cell frequency of zero to calculate the Mantel-Haenszel estimate and
he advocates the exact method (MH.exact=TRUE). Note, the
estimate based on the exact method is not defined if the number of
events is zero in all studies either in the experimental or control
group.
A prediction interval for treatment effect of a new study is
calculated (Higgins et al., 2009) if arguments prediction and
comb.random are TRUE.
R function update.meta can be used to redo the
meta-analysis of an existing metabin object by only specifying
arguments which should be changed.
If R package metafor (Viechtbauer 2010) is installed, the following statistical methods are also available.
For the random effects model (argument comb.random=TRUE), the
method by Hartung and Knapp (Hartung, Knapp 2001; Knapp, Hartung
2003) is used to adjust test statistics and confidence intervals if
argument hakn=TRUE (internally R function rma.uni of R
package metafor is called).
Several methods are available to estimate the between-study variance
$\tau^2$ (argument method.tau):
method.tau="DL") (default)method.tau="REML")method.tau="ML")method.tau="HS")method.tau="SJ")method.tau="HE")method.tau="EB").rma.uni of R package metafor is called internally. See help
page of R function rma.uni for more details on the various
methods to estimate between-study variance $\tau^2$.Diamond GA, Bax L, Kaul S (2007), Uncertain Effects of Rosiglitazone on the Risk for Myocardial Infarction and Cardiovascular Death. Annals of Internal Medicine, 147, 578--581.
DerSimonian R & Laird N (1986), Meta-analysis in clinical trials. Controlled Clinical Trials, 7, 177--188.
Fleiss JL (1993), The statistical basis of meta-analysis. Statistical Methods in Medical Research, 2, 121--145.
Greenland S & Robins JM (1985), Estimation of a common effect parameter from sparse follow-up data. Biometrics, 41, 55--68.
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. Higgins JPT, Thompson SG, Spiegelhalter DJ (2009), A re-evaluation of random-effects meta-analysis. Journal of the Royal Statistical Society: Series A, 172, 137-159.
Knapp G & Hartung J (2003), Improved Tests for a Random Effects Meta-regression with a Single Covariate. Statistics in Medicine, 22, 2693-710, doi: 10.1002/sim.1482 . Review Manager (RevMan) [Computer program]. Version 5.1. Copenhagen: The Nordic Cochrane Centre, The Cochrane Collaboration, 2011.
Pettigrew HM, Gart JJ, Thomas DG (1986), The bias and higher cumulants of the logarithm of a binomial variate. Biometrika, 73, 425--435.
Ruecker G, Schwarzer G, Carpenter JR (2008) Arcsine test for publication bias in meta-analyses with binary outcomes. Statistics in Medicine, 27, 746--763. StataCorp. 2011. Stata Statistical Software: Release 12. College Station, TX: StataCorp LP. Sweeting MJ, Sutton AJ, Lambert PC (2004), What to add to nothing? Use and avoidance of continuity corrections in meta-analysis of sparse data. Statistics in Medicine, 23, 1351--1375.
Viechtbauer W (2010), Conducting Meta-Analyses in R with the Metafor Package. Journal of Statistical Software, 36, 1--48.
update.meta, funnel, metabias, metacont, metagen, print.metametabin(10, 20, 15, 20, sm="OR", warn=FALSE)
##
## Different results:
##
metabin(0, 10, 0, 10, sm="OR", warn=FALSE)
metabin(0, 10, 0, 10, sm="OR", allstudies=TRUE, warn=FALSE)
data(Olkin95)
meta1 <- metabin(event.e, n.e, event.c, n.c,
data=Olkin95, subset=c(41,47,51,59),
sm="RR", method="I")
summary(meta1)
funnel(meta1)
meta2 <- metabin(event.e, n.e, event.c, n.c,
data=Olkin95, subset=Olkin95$year<1970,
sm="RR", method="I")
summary(meta2)
forest(meta2)Run the code above in your browser using DataLab