effect_measures: Calculate the effect measures

In FrankLef/fciR: Data and functions used with Fundamentals of Causal Inference by Babette Brumback

Calculate the effect measures

Description

Calculate the effect measures.

Usage

effect_measures(val0, val1, log = TRUE)

Arguments

val0	Numeric, base value
val1	Numeric, treated value
log	If TRUE (default) compute the effect measures on the log scale. If FALSE compute the effect measures on the natural scale. The risk difference measure (RD) is always on the natural scale.

Details

Calculate the effect measures and put them in a named numeric() vector. If log = TRUE the measures are RD (risk difference), logRR (log of relative risk), logRR* (log of other relative risk) and logOR (log of odds ratio). If log = FALSE the measures are RD (risk difference), logRR (relative risk), logRR* (other relative risk) and logOR (odds ratio). See section 3.3 for more details on these measures.

Value

Named numeric vector.

Examples

val0 <- 0.25
val1 <- 0.5
# when log is required, we use default value
out <- effect_measures(val0, val1)
stopifnot(all(is.finite(out)))
# when natural scale is required, we use log = FALSE
out <- effect_measures(val0, val1, log = FALSE)
stopifnot(all(is.finite(out)))

FrankLef/fciR documentation built on Nov. 12, 2023, 6:09 a.m.