
Compute HSMD effect-size columns
hsmd_effect_sizes.RdCompute HSMD effect-size columns
Usage
hsmd_effect_sizes(
data,
mT,
sdT,
nT,
mC,
sdC,
nC,
probs = c(0.25, 0.5, 0.75),
cv_by = NULL,
cv_benchmarks = NULL
)Arguments
- data
A data frame containing treatment and control summary statistics.
- mT, sdT, nT
Unquoted column names for treatment-group mean, standard deviation, and sample size. Observed values must be finite numeric values; sample sizes must be integers greater than 1 and SDs non-negative. Missing SDs are permitted when benchmarks can be estimated or supplied.
- mC, sdC, nC
Unquoted column names for control-group mean, standard deviation, and sample size.
- probs
Numeric vector of coefficient-of-variation quantiles to use for harmonization. Defaults to
c(0.25, 0.50, 0.75). Values must be distinct and strictly between zero and one. Decimal percentage labels usep, so 0.251 generates columns such asd25p1.- cv_by
Optional unquoted column used to compute coefficient-of-variation benchmarks within subgroups, such as outcomes or domains. Group IDs cannot be missing. One or several quantiles may be requested.
- cv_benchmarks
Optional named list with elements
treatmentandcontrol, each a positive finite numeric vector aligned withprobs. Withcv_by, provide matrices/data frames whose row names identify groups and whose columns followprobsin the supplied order.
Value
A list with prepared data, effect_sizes, probs, prob_names,
and coefficient-of-variation benchmarks.
Examples
hsmd_cols <- hsmd_effect_sizes(
hsmd_example_1,
mT = mT,
sdT = sdT,
nT = nT,
mC = mC,
sdC = sdC,
nC = nC
)
names(hsmd_cols$effect_sizes)
#> [1] "d" "vd" "g" "vg" "d25" "vd25" "g25" "vg25" "d50" "vd50"
#> [11] "g50" "vg50" "d75" "vd75" "g75" "vg75"