Conditional Relative Risk estimation via Double Machine Learning
crr(
treatment,
response_model,
propensity_model,
importance_model,
contrast = c(1, 0),
data,
nfolds = 5,
type = "dml1",
...
)
formula specifying treatment and variables to condition on
SL object
SL object
SL object
treatment contrast (default 1 vs 0)
data.frame
Number of folds
'dml1' or 'dml2'
additional arguments to SuperLearner
cate.targeted object
sim1 <- function(n=1e4,
seed=NULL,
return_model=FALSE, ...){
suppressPackageStartupMessages(require("lava"))
if (!is.null(seed)) set.seed(seed)
m <- lava::lvm()
distribution(m, ~x) <- gaussian.lvm()
distribution(m, ~v) <- gaussian.lvm(mean = 10)
distribution(m, ~a) <- binomial.lvm("logit")
regression(m, "a") <- function(v, x){.1*v + x}
distribution(m, "y") <- gaussian.lvm()
regression(m, "y") <- function(a, v, x){v+x+a*x+a*v*v}
if (return_model) return(m)
lava::sim(m, n = n)
}
d <- sim1(n = 1e4, seed = 1)
if (require("SuperLearner",quietly=TRUE)) {
e <- crr(data=d,
type = "dml2",
treatment = a ~ v,
response_model = y~ a*(x + v + I(v^2)),
importance_model = SL(D_ ~ v + I(v^2)),
nfolds = 10)
summary(e) # the true parameters are c(1,1)
}
#> crr(treatment = a ~ v, response_model = y ~ a * (x + v + I(v^2)),
#> importance_model = SL(D_ ~ v + I(v^2)), data = d, nfolds = 10,
#> type = "dml2")
#>
#> Estimate Std.Err 2.5% 97.5% P-value
#> (Intercept) 0.9972 0.24776 0.5116 1.483 5.702e-05
#> v 1.0014 0.02447 0.9534 1.049 0.000e+00