Qt: Measures of covariate heterogeneity

In ipdmeta: Tools for subgroup analyses with multiple trial data using aggregate statistics

Description

Measures of covariate heterogeneity proposed by Simmonds and Higgins (2007) for assessing the power of a meta-regression

Usage

Qt(m,n,sigma2)

Arguments

m	vector of study-level covariate means
n	vector of study sample sizes
sigma2	vector of covariate sample variances

Value

A list with the following named components: t, Qd, Qe, bar.Qd,bar.Qe, tilde.Qd, tilde.Qe

Author(s)

S. Kovalchik [e-mail]

References

Simmonds, M. C., Higgins, J. P. T., (2007), Covariate heterogeneity in meta-analysis: criteria for deciding between meta-regression and individual patient data, Statistics in Medicine, 26 (15): 2982-99.

Examples

data(poynard)

#COVARIATE HETEROGENEITY FOR AGE

m <- (poynard$n0*poynard$age0+poynard$n1*poynard$age1)/(poynard$n0+poynard$n1)
n <- poynard$n0+poynard$n1
sigma2 <- ((poynard$n0-1)*poynard$age.s20+(poynard$n1-1)*poynard$age.s21)/(poynard$n0+poynard$n1-2)


Q <- Qt(m,n,sigma2)

lapply(Q,function(x){x/Q$t})

ipdmeta documentation built on May 2, 2019, 3:29 p.m.