meta.sub.semipart

Computes the estimate, standard error, and confidence interval
for a difference in average semipartial correlations for two
subgroups of mutually exclusive studies. Each subgroup can
have one or more studies.

Implements functions for varying coefficient meta-analysis methods.
These methods do not assume effect size homogeneity. Subgroup effect size
comparisons, general linear effect size contrasts, and linear models of
effect sizes based on varying coefficient methods can be used to describe
effect size heterogeneity. Varying coefficient meta-analysis methods do not
require the unrealistic assumptions of the traditional fixed-effect and
random-effects meta-analysis methods. For details see:
Statistical Methods for Psychologists, Volume 5, <https://dgbonett.sites.ucsc.edu/>.

Douglas G. Bonett

vcmeta

Varying Coefficient Meta-Analysis

Robert J. Calin-Jageman

meta.sub.semipart function

<dl><dt>alpha</dt>
<dd>alpha level for 1-alpha confidence</dd>
<dt>n</dt>
<dd>vector of sample sizes</dd>
<dt>cor</dt>
<dd>vector of estimated semi-partial correlations</dd>
<dt>r2</dt>
<dd>vector of squared multiple correlations for a model that
includes the IV and all control variables</dd>
<dt>group</dt>
<dd>vector of group indicators:<ul>
<li>1 for set A</li>
<li>2 for set B</li>
<li>0 to ignore</li>
</ul></dd></dl>

Arguments

Confidence interval for a subgroup difference in average
semipartial correlations — meta.sub.semipart

<dl>

<dt>alpha</dt>
<dd>alpha level for 1-alpha confidence</dd>


<dt>n</dt>
<dd>vector of sample sizes</dd>


<dt>cor</dt>
<dd>vector of estimated semi-partial correlations</dd>


<dt>r2</dt>
<dd>vector of squared multiple correlations for a model that
includes the IV and all control variables</dd>


<dt>group</dt>
<dd>vector of group indicators:<ul>
<li>1 for set A</li>
<li>2 for set B</li>
<li>0 to ignore</li>
</ul></dd>

</dl>

meta.sub.semipart: Confidence interval for a subgroup difference in average semipartial correlations

Description

Usage

Value

Arguments

Examples