psychmeta (version 2.3.4)

convert_es: Convert effect sizes and compute confidence intervals

Description

This function converts a variety of effect sizes to either correlations or Cohen's d values. The function also computes and prints confidence intervals for the output effect sizes.

Usage

convert_es(es, input_es = c("r", "d", "delta", "g", "t", "p.t", "F",
  "p.F", "chisq", "p.chisq", "or", "lor", "Fisherz", "A", "auc", "cles"),
  output_es = c("r", "d", "A", "auc", "cles"), n1 = NULL, n2 = NULL,
  df1 = NULL, df2 = NULL, sd1 = NULL, sd2 = NULL,
  correct_bias = TRUE, conf_level = 0.95)

Arguments

es

Vector of effect sizes to convert.

input_es

Metric of input effect sizes. Currently supports correlations, Cohen's d, independent samples t values (or their p values), two-group one-way ANOVA F values (or their p values), 1df \(\chi^{2}\) values (or their p values), odds ratios, log odds ratios, Fisher z, and the common language effect size (CLES, A, AUC).

output_es

Metric of output effect sizes. Currently supports correlations, Cohen's d values, and common language effect sizes (CLES, A, AUC).

n1

Vector of total sample sizes or sample sizes of group 1 of the two groups being contrasted.

n2

Vector of sample sizes of group 2 of the two groups being contrasted.

df1

Vector of input test statistic degrees of freedom (for t and \(\chi^{2}\)) or between-groups degree of freedom (for F).

df2

Vector of input test statistic within-group degrees of freedom (for F).

sd1

Vector of pooled (within-group) standard deviations or standard deviations of group 1 of the two groups being contrasted.

sd2

Vector of standard deviations of group 2 of the two groups being contrasted.

correct_bias

Logical argument that determines whether to correct output effect sizes and error-variance estimates for small-sample bias (TRUE) or not (FALSE) when computing confidence intervals.

conf_level

Confidence level that defines the width of the confidence interval (default = .95).

Value

A psychmeta effect size es object containing:

meta_input

A matrix of converted effect sizes and adjusted sample sizes for use in subsequent meta-anlayses.

original_es

The input data.

confidence

The output data with computed confidence intervals (for printing).

Notes

To use converted effect sizes in a meta-analysis, add the values from es$meta_input to your meta-analytic input data frame.

References

Chinn, S. (2000). A simple method for converting an odds ratio to effect size for use in meta-analysis. Statistics in Medicine, 19(22), 3127<U+2013>3131. https://doi.org/10/c757hm

Lipsey, M. W., & Wilson, D. B. (2001). Practical meta-analysis. Thousand Oaks, CA: SAGE.

Ruscio, J. (2008). A probability-based measure of effect size: Robustness to base rates and other factors. Psychological Methods, 13(1), 19<U+2013>30. https://doi.org/10.1037/1082-989X.13.1.19

Schmidt, F. L., & Hunter, J. E. (2015). Methods of meta-analysis: Correcting error and bias in research findings (3rd ed.). Thousand Oaks, CA: SAGE. https://doi.org/10/b6mg

Examples

# NOT RUN {
## To convert a statistic to r or d metric:
convert_es(es = 1,  input_es="d", output_es="r", n1=100)
convert_es(es = 1, input_es="d", output_es="r", n1=50, n2 = 50)
convert_es(es = .2, input_es="r", output_es="d",  n1=100, n2=150)
convert_es(es = -1.3, input_es="t", output_es="r", n1 = 100, n2 = 140)
convert_es(es = 10.3, input_es="F", output_es="d", n1 = 100, n2 = 150)
convert_es(es = 1.3, input_es="chisq", output_es="r", n1 = 100, n2 = 100)
convert_es(es = .021, input_es="p.chisq", output_es="d", n1 = 100, n2 = 100)
convert_es(es = 4.37, input_es="or", output_es="r", n1=100, n2=100)
convert_es(es = 4.37, input_es="or", output_es="d", n1=100, n2=100)
convert_es(es = 1.47, input_es="lor", output_es="r", n1=100, n2=100)
convert_es(es = 1.47, input_es="lor", output_es="d", n1=100, n2=100)

## To simply compute a confidence interval for r, d, or A:
convert_es(es = .3,  input_es="r", output_es="r", n1=100)
convert_es(es = .8,  input_es="d", output_es="d", n1=64, n2=36)
convert_es(es = .8,  input_es="A", output_es="A", n1=64, n2=36)
# }