meta.sub.cor {vcmeta}

Confidence interval for a difference in average Pearson or partial correlations for two sets of studies

Description

Computes the estimate, standard error, and confidence interval for a difference in average Pearson or partial correlations for two mutually exclusive sets of studies. Each set can have one or more studies. All of the correlations must be either Pearson correlations or partial correlations.

Usage

meta.sub.cor(alpha, n, cor, s, group)

Arguments

alpha

alpha level for 1-alpha confidence

n

vector of sample sizes

cor

vector of estimated Pearson correlations

s

number of control variables (set to 0 for Pearson)

group

vector of group indicators:

• 1 for set A

• 2 for set B

• 0 to ignore

Value

Returns a matrix with three rows:

• Row 1 - estimate for Set A

• Row 2 - estimate for Set B

• Row 3 - estimate for difference, Set A - Set B

The columns are:

• Estimate - estimated average correlation or difference

• SE - standard error

• LL - lower limit of the confidence interval

• UL - upper limit of the confidence interval

References

Bonett DG (2008). “Meta-analytic interval estimation for bivariate correlations.” Psychological Methods, 13(3), 173–181. ISSN 1939-1463, doi:10.1037/a0012868.

Examples

n <- c(55, 190, 65, 35)
cor <- c(.40, .65, .60, .45)
group <- c(1, 1, 2, 0)
meta.sub.cor(.05, n, cor, 0, group)

# Should return:
#                Estimate         SE         LL        UL
# Set A:            0.525 0.06195298  0.3932082 0.6356531
# Set B:            0.600 0.08128008  0.4171458 0.7361686
# Set A - Set B:   -0.075 0.10219894 -0.2645019 0.1387283