psychmeta (version 0.2.4)

ma_r_order2: Second-order meta-analysis function for correlations

Description

This function computes second-order meta-analysis function for correlations. It supports second-order analyses of bare-bones, artifact-distribution, and individual-correction meta-analyses.

Usage

ma_r_order2(r = NULL, rho = NULL, var_r = NULL, var_r_c = NULL,
  k = NULL, ma_type = c("bb", "ic", "ad"), sample_id = NULL,
  moderators = NULL, moderator_type = "simple", construct_x = NULL,
  construct_y = NULL, conf_level = 0.95, cred_level = 0.8,
  conf_method = "t", cred_method = "t", var_unbiased = TRUE,
  hs_override = FALSE, data = NULL)

Arguments

r

Vector or column name of mean observed correlations.

rho

Vector or column name of mean corrected correlations.

var_r

Vector or column name of observed variances of observed correlations.

var_r_c

Vector or column name of observed variances of corrected correlations.

k

Vector or column name of meta-analyses' k values.

ma_type

Type of meta-analyses being analyzed: "bb" (barebones), "ic" (individual correction), or "ad" (artifact distribution).

sample_id

Vector or column name of study ID labels.

moderators

Matrix or column names of moderator variables to be used in the meta-analysis (can be a vector in the case of one moderator).

moderator_type

Type of moderator analysis ("none", "simple", or "hierarchical").

construct_x

Vector or column name of construct names for X.

construct_y

Vector or column name of construct names for Y.

conf_level

Confidence level to define the width of the confidence interval (default = .95).

cred_level

Credibility level to define the width of the credibility interval (default = .80).

conf_method

Distribution to be used to compute the width of confidence intervals. Available options are "t" for t distribution or "norm" for normal distribution.

cred_method

Distribution to be used to compute the width of credibility intervals. Available options are "t" for t distribution or "norm" for normal distribution.

var_unbiased

Logical scalar determining whether variances should be unbiased (TRUE) or maximum-likelihood (FALSE).

hs_override

When TRUE, this will override settings for conf_method (will set to "norm"), cred_method (will set to "norm"), and var_unbiased (will set to FALSE).

data

Data frame containing columns whose names may be provided as arguments to vector arguments and/or moderators.

Value

An object of the classes psychmeta, ma_r_as_r, ma_order2, and ma_bb, ma_ic, and/or ma_ad.

Examples

# NOT RUN {
## Analysis of the validity of conscientiousness as a predictor of job performance in East Asia
ma_r_order2(r = r_bar_i, rho = rho_bar_i, var_r = var_r,
            var_r_c = NULL, k = k, ma_type = "ad",
            sample_id = NULL, moderators = NULL,
            construct_x = NULL, construct_y = NULL,
            conf_level = .95, cred_level = .8,
            cred_method = "t", var_unbiased = TRUE,
            data = dplyr::filter(data_r_oh_2009, Predictor == "Conscientiousness"))

## Analysis of the validity of the Big Five traits as predictors of job performance in East Asia
ma_r_order2(r = r_bar_i, rho = rho_bar_i, var_r = var_r,
            var_r_c = NULL, k = k, ma_type = "ad",
            sample_id = NULL, moderators = NULL, construct_x = Predictor,
            conf_level = .95, cred_level = .8,
            cred_method = "t", var_unbiased = TRUE,
            data = data_r_oh_2009)

## Analysis of the average validity of the Big Five traits as predictors of
## job performance by Eastern Asian country
ma_r_order2(r = r_bar_i, rho = rho_bar_i, var_r = var_r,
            var_r_c = NULL, k = k, ma_type = "ad",
            sample_id = NULL, moderators = "Country",
            conf_level = .95, cred_level = .8, cred_method = "t",
            var_unbiased = TRUE, data = data_r_oh_2009)
# }