Computes the estimate and standard error for a 2-group proportion difference

Source: R/meta_se.R

This function computes the Agresti-Caffo standard error of a 2-group proportion difference using the frequency counts and sample sizes. The effect size estimate and standard error output from this function can be used as input in the meta.ave.gen, meta.lc.gen, and meta.lm.gen functions in applications where compatible proportion differences from a combination of 2-group and paired-samples studies are used in the meta-analysis.

se.prop2(f1, f2, n1, n2)

Arguments

f1

number of participants in group 1 who have the outcome

f2

number of participants in group 2 who have the outcome

n1

sample size for group 1

n2

sample size for group 2

Value

Returns a one-row matrix:

  • Estimate - estimated proportion difference

  • SE - standard error

References

Agresti A, Caffo B (2000). “Simple and Effective Confidence Intervals for Proportions and Differences of Proportions Result from Adding Two Successes and Two Failures.” The American Statistician, 54(4), 280-288. doi:10.1080/00031305.2000.10474560 .

Examples

se.prop2(31, 16, 40, 40)
#>                          Estimate        SE
#> Proportion difference:  0.3571429 0.1002777

# Should return:
#                          Estimate        SE
# Proportion difference:  0.3571429 0.1002777