plot.infl.rma.uni: Plot Method for 'infl.rma.uni' Objects

Description

Plot method for objects of class "infl.rma.uni".

Usage

## S3 method for class 'infl.rma.uni':
plot(x, plotinf=TRUE, plotdfb=FALSE, dfbnew=FALSE, logcov=TRUE,
     layout, slab.style=1, las=0, pch=21, bg="black",
     bg.infl="red", col.na="lightgray", \dots)

Arguments

an object of class "infl.rma.uni".

plotinf

logical indicating whether the various case diagnostics should be plotted (default is TRUE). Can also be a vector of up to 8 integers indicating which plots to draw (see Details for the numbers corresponding to the various pl

plotdfb

logical indicating whether the DFBETAS values should be plotted (default is FALSE). Can also be a vector of integers to indicate for which coefficient(s) to plot the DFBETAS values.

dfbnew

logical indicating whether a new device should be opened for plotting the DFBETAS values (default is FALSE).

logcov

logical indicating whether the covariance ratios should be plotted on a log scale (default is TRUE).

layout

optional vector of two numbers, indicating the number of rows and columns for the layout of the figure.

slab.style

integer to indicate the style of the x-axis labels: 1 = study number, 2 = study label, 3 = abbreviated study label. Note that study labels, even when abbreviated, may be too long to fit in the margin.)

las

integer between 0 and 3 to specify the alignment of the axis labels (see par). The most useful alternative to 0 is 3, so that the x-axis labels are drawn vertical to the axis.

pch

plotting symbol to use. By default, a filled circle is used. See points for other options.

color to use for filling the plotting symbol (default is "black").

bg.infl

color to use for filling the plotting symbol when the point is considered influential (default is "red").

col.na

color to use for lines connecting two points with NA values in between (default is "lightgray").

...

other arguments.

Details

When plotinf=TRUE, the function plots the (1) externally standardized residuals, (2) DFFITS values, (3) Cook's distances, (4) covariance ratios, (5) leave-one-out latex{$\tau^2$}html{$\tau²$}text{$\tau^2$} estimates, (6) leave-one-out (residual) heterogeneity test statistics, (7) hat values, and (8) weights. If plotdfb=TRUE, the DFBETAS values are also plotted either after confirming the page change (if newdfb=FALSE) or on a separate device (if newdfb=TRUE). A study may be considered to be influential if at least one of the following is true:

The absolute DFFITS value is larger than$3\sqrt{p/(k-p)}$, where$p$is the number of model coefficients and$k$the number of studies.
The lower tail area of a chi-square distribution with$p$degrees of freedom cut off by the Cook's distance is larger than 50\%.
The hat value is larger than$3(p/k)$.
Any DFBETAS value is larger than$1$.

Studies which are considered influential with respect to any of these measures are indicated by the color specified for the bg.infl argument (the default is "red"). The cut-offs described above are indicated in the plot with horizontal reference lines. In addition, on the plot of the externally standardized residuals, horizontal reference lines are drawn at -1.96, 0, and 1.96. On the plot of the hat values, a horizontal reference line is drawn at $p/k$. Since the sum of the hat values is equal to $p$, the value $p/k$ indicates equal hat values for all $k$ studies. Finally, on the plot of weights, a horizontal reference line is drawn at $100/k$, corresponding to the value for equal weights (in %) for all $k$ studies. Note that all weights will automatically be equal to each other when using unweighted model fitting. Also, the hat values will be equal to the weights values (except for their scaling) in models without moderators. The chosen cut-offs are (somewhat) arbitrary. Substantively informed judgment should always be used when examining the influence of each study on the results.

References

Viechtbauer, W. (2010). Conducting meta-analyses in R with the metafor package. Journal of Statistical Software, 36(3), 1--48. http://www.jstatsoft.org/v36/i03/. Viechtbauer, W., & Cheung, M. W.-L. (2010). Outlier and influence diagnostics for meta-analysis. Research Synthesis Methods, 1, 112--125.

Examples

Run this code

### load BCG vaccine data
data(dat.bcg)

### meta-analysis of the log relative risks using a mixed-effects model
### with two moderators (absolute latitude and publication year)
res <- rma(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg,
           mods = ~ ablat + year, data=dat.bcg)
plot(influence(res))
plot(influence(res), plotinf=1:4)
plot(influence(res), plotinf=1:4, layout=c(4,1))
plot(influence(res), plotdfb=TRUE)