meta (version 0.5)

metabias: Test for funnel plot asymmetry

Description

Test for funnel plot asymmetry, based on rank correlation or linear regression method.

Usage

metabias(x, seTE, TE.fixed, seTE.fixed,
         method = "rank",
         plotit = FALSE, correct = FALSE)

Arguments

x

An object of class meta, or estimated treatment effect in individual studies.

seTE

Standard error of estimated treatment effect (mandatory if x not of class meta).

TE.fixed

Overall treatment estimate (mandatory if x not of class meta and method = "rank").

seTE.fixed

Standard error of overall treatment estimate (mandatory if x not of class meta and method = "rank").

method

A character string indicating which test is to be used. Either "rank", "linreg", "mm" or "count", can be abbreviated.

plotit

A logical indicating whether a plot should be produced for method "rank", "linreg" or "mm".

correct

A logical indicating whether a continuity corrected statistic is used for rank correlation methods "rank" and "count".

Value

• A list with class "htest" containing the following components:
• estimate
  the estimated degree of funnel plot asymmetry, with name "ks" or "bias" corresponding to the method employed, i.e., rank correlation or regression method.
• statistic
  The value of the test statistic.
• parameter
  The degrees of freedom of the test statistic in the case that it follows a t distribution.
• p.value
  The p-value for the test.
• null.value
  The value of test statistic under the null hypothesis, always 0.
• alternative
  A character string describing the alternative hypothesis.
• method
  A character string indicating what type of test was used.
• data.name
  A character string giving the names of the data.

Details

If method is "rank", the test statistic is based on the rank correlation between standardised treatment estimates and variance estimates of estimated treatment effects; Kendall's tau is used as correlation measure (Begg & Mazumdar, 1994). The test statistic follows a standard normal distribution. By default (if correct is FALSE), no continuity correction is utilised (Kendall & Gibbons, 1990). If method is "linreg", the test statistic is based on a linear regression of the standardised treatment effect (standard normal deviate) on the inverse of the standard error of the treatment estimate (Egger et al., 1997). The test statistic follows a t distribution with number of studies - 2 degrees of freedom. If method is "mm", the test statistic is based on a weighted linear regression using the method of moments estimator of the additive between-study variance component (method 3a in Thompson, Sharp, 1999). The test statistic follows a t distribution with number of studies - 2 degrees of freedom.

If method is "count", the test statistic is based on the rank correlation between a standardised cell frequency and the inverse of the variance of the cell frequency; Kendall's tau is used as correlation measure (Schwarzer, 2003). The test statistic follows a standard normal distribution. By default (if correct is FALSE), no continuity correction is utilised (Kendall & Gibbons, 1990).

References

Begg CB & Berlin JA (1994), Operating characteristics of a rank correlation test for publication bias. Biometrics, 50, 1088--1101.

Kendall M & Gibbons JD (1990), Rank Correlation Methods. London: Edward Arnold.

Egger M, Smith GD, Schneider M & Minder C (1997), Bias in meta-analysis detected by a simple, graphical test. British Medical Journal, 315, 629--634.

Schwarzer G (2003), Statistical Tests for Bias in Meta-Analysis with Binary Outcomes, PhD thesis, University of Dortmund, Germany, http://eldorado.uni-dortmund.de

Thompson SG, Sharp, SJ (1999), Explaining heterogeneity in meta-analysis: A comparison of methods, Statistics in Medicine, 18, 2693--2708.

See Also

funnel, metabin, metacont, metagen

Examples

data(Olkin95)
meta1 <- metabin(event.e, n.e, event.c, n.c,
                 data=Olkin95, subset=c(41,47,51,59),
                 sm="RR", meth="I")

metabias(meta1)
metabias(meta1, correct=TRUE)

metabias(meta1, method="linreg")
metabias(meta1, method="linreg", plotit=TRUE)


metabias(meta1, method="count")

##
## Same result:
##
metabias(meta1, method="linreg")$p.value
metabias(meta1$TE, meta1$seTE, method="linreg")$p.value