Learn R Programming

metaSEM (version 1.4.0)

Gleser94: Two Datasets from Gleser and Olkin (1994)

Description

It includes two datasets in multiple-treatment studies and multiple-endpoint studies reported by Gleser and Olkin (1994).

Usage

data("Gleser94")

Arguments

Format

A list of two data frames.

MTS

A data frame of multiple-treatment studies.

MES

A data frame of multiple-endpoint studies.

See Also

smdMTS, smdMES

Examples

Run this code
# \donttest{
data(Gleser94)

#### Multiple-treatment studies
Gleser94$MTS

## Assuming homogeneity of variances
my.MTS <- t(apply(Gleser94$MTS, MARGIN=1,
            function(x)
            smdMTS(m=x[c("Mean.C", "Mean.E1", "Mean.E2", "Mean.E3", "Mean.E4", "Mean.E5")],
                   v=x[c("SD.C", "SD.E1", "SD.E2", "SD.E3", "SD.E4", "SD.E5")]^2,
                   n=x[c("N.C", "N.E1", "N.E2", "N.E3", "N.E4", "N.E5")],
                   homogeneity="variance", list.output=FALSE)))

## Fixed-effects multivariate meta-analysis
fit.MTS <- meta(y=my.MTS[, 1:5], 
                v=my.MTS[, 6:20], 
                RE.constraints = diag(0, ncol=5, nrow=5),
                model.name="MTS")
summary(fit.MTS)

#### Multiple-endpoint studies
Gleser94$MES

## Calculate the sampling variances and covariance and amend into the data set
Gleser94$MES$Uncoached.V11 <- with(Gleser94$MES, SD.Uncoached.Math^2)
Gleser94$MES$Uncoached.V21 <- with(Gleser94$MES,
                                   SD.Uncoached.Math*Cor.Math.Verbal*SD.Uncoached.Verbal)
Gleser94$MES$Uncoached.V22 <- with(Gleser94$MES, SD.Uncoached.Verbal^2)

Gleser94$MES$Coached.V11 <- with(Gleser94$MES, SD.Coached.Math^2)
Gleser94$MES$Coached.V21 <- with(Gleser94$MES,
                                 SD.Coached.Math*Cor.Math.Verbal*SD.Coached.Verbal)
Gleser94$MES$Coached.V22 <- with(Gleser94$MES, SD.Coached.Verbal^2)

## Assuming homogeneity of covariance matrices
my.MES <- t(apply(Gleser94$MES, MARGIN=1,
            function(x)
            smdMES(m1=x[c("Mean.Uncoached.Math", "Mean.Uncoached.Verbal")],
                   m2=x[c("Mean.Coached.Math", "Mean.Coached.Verbal")],
                   V1=vec2symMat(x[c("Uncoached.V11", "Uncoached.V21", "Uncoached.V22")]),
                   V2=vec2symMat(x[c("Coached.V11", "Coached.V21", "Coached.V22")]),
                   n1=x["N.Uncoached"],
                   n2=x["N.Coached"],
                   homogeneity="covariance", list.output=FALSE)))

## Fixed-effects multivariate meta-analysis
fit.MES <- meta(y=my.MES[, 1:2], 
                v=my.MES[, 3:5], 
                RE.constraints = diag(0, ncol=2, nrow=2),
                model.name="MES")
summary(fit.MES)
# }

Run the code above in your browser using DataLab