leave1out: Leave-One-Out Diagnostics for 'rma' Objects

In wviechtb/metafor: Meta-Analysis Package for R

Leave-One-Out Diagnostics for 'rma' Objects

Description

Functions to carry out a ‘leave-one-out analysis’, by repeatedly fitting the specified model leaving out one study (or cluster level) at a time. \loadmathjax

Usage

leave1out(x, ...)

## S3 method for class 'rma.uni'
leave1out(x, cluster, digits, transf, targs, progbar=FALSE, ...)
## S3 method for class 'rma.mh'
leave1out(x, cluster, digits, transf, targs, progbar=FALSE, ...)
## S3 method for class 'rma.peto'
leave1out(x, cluster, digits, transf, targs, progbar=FALSE, ...)

Arguments

x	an object of class "rma.uni", "rma.mh", or "rma.peto".
cluster	optional vector to specify a clustering variable.
digits	optional integer to specify the number of decimal places to which the printed results should be rounded. If unspecified, the default is to take the value from the object.
transf	optional argument to specify a function to transform the model coefficients and interval bounds (e.g., transf=exp; see also transf). If unspecified, no transformation is used.
targs	optional arguments needed by the function specified under transf.
progbar	logical to specify whether a progress bar should be shown (the default is FALSE).
...	other arguments.

Details

In a leave-one-out analysis, the same model is repeatedly fitted, leaving out one study at a time. By doing so, we can assess how much the results are influenced by each individual study. It is also possible to specify a cluster variable, in which case each cluster level is left out in turn.

Note that for "rma.uni" objects, the model specified via x must be a model without moderators (i.e., either an equal- or a random-effects model).

Value

An object of class "list.rma". The object is a list containing the following components:

estimate	estimated (average) outcomes.
se	corresponding standard errors.
zval	corresponding test statistics.
pval	corresponding p-values.
ci.lb	lower bounds of the confidence intervals.
ci.ub	upper bounds of the confidence intervals.
Q	test statistics for the test of heterogeneity.
Qp	corresponding p-values.
tau2	estimated amount of heterogeneity (only for random-effects models).
I2	values of \mjseqnI^2.
H2	values of \mjseqnH^2.

When the model was fitted with test="t", test="knha", test="hksj", or test="adhoc", then zval is called tval in the object that is returned by the function.

The object is formatted and printed with the print function. To format the results as a data frame, one can use the as.data.frame function.

Note

When using the transf option, the transformation is applied to the estimated coefficients and the corresponding interval bounds. The standard errors are then set equal to NA and are omitted from the printed output.

The variable specified via cluster is assumed to be of the same length as the data originally passed to the model fitting function (and if the data argument was used in the original model fit, then the variable will be searched for within this data frame first). Any subsetting and removal of studies with missing values that was applied during the model fitting is also automatically applied to the variable specified via the cluster argument.

Author(s)

Wolfgang Viechtbauer ([e-mail], https://www.metafor-project.org).

References

Viechtbauer, W. (2010). Conducting meta-analyses in R with the metafor package. Journal of Statistical Software, 36(3), 1–48. ⁠https://doi.org/10.18637/jss.v036.i03⁠

Viechtbauer, W. (2021). Model checking in meta-analysis. In C. H. Schmid, T. Stijnen, & I. R. White (Eds.), Handbook of meta-analysis (pp. 219–254). Boca Raton, FL: CRC Press. ⁠https://doi.org/10.1201/9781315119403⁠

Viechtbauer, W., & Cheung, M. W.-L. (2010). Outlier and influence diagnostics for meta-analysis. Research Synthesis Methods, 1(2), 112–125. ⁠https://doi.org/10.1002/jrsm.11⁠

See Also

rma.uni, rma.mh, and rma.peto for functions to fit models for which leave-one-out diagnostics can be computed.

Examples

### calculate log risk ratios and corresponding sampling variances
dat <- escalc(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg)

### random-effects model
res <- rma(yi, vi, data=dat)

### leave-one-out analysis
leave1out(res)
leave1out(res, transf=exp)

### leave-one-out analysis with a cluster variable
leave1out(res, cluster=alloc)

### meta-analysis of the (log) risk ratios using the Mantel-Haenszel method
res <- rma.mh(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg)

### leave-one-out analysis
leave1out(res)
leave1out(res, transf=exp)

### meta-analysis of the (log) odds ratios using Peto's method
res <- rma.peto(ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg)

### leave-one-out analysis
leave1out(res)
leave1out(res, transf=exp)

wviechtb/metafor documentation built on Dec. 4, 2024, 1:03 a.m.