`tmle_NDE` and `tmle_NIE` give `error: W not found`

[agusinac]

Hello, I have tried to use the tmle_NDE and tmle_NIE functions to get the direct/indirect effects besides the total effect I only get with tmle_medshift. Below the code I am using with your example_data.

# produces a simple data set based on ca causal model with mediation
make_mediation_data <- function(n_obs = 1000) {
  # baseline covariate -- simple, binary
  W <- rbinom(n_obs, 1, prob = 0.50)

  # create treatment based on baseline W
  A <- as.numeric(rbinom(n_obs, 1, prob = W / 4 + 0.1))

  # single mediator to affect the outcome
  z1_prob <- 1 - plogis((A^2 + W) / (A + W^3 + 0.5))
  Z <- rbinom(n_obs, 1, prob = z1_prob)

  # create outcome as a linear function of A, W + white noise
  Y <- Z + A - 0.1 * W + rnorm(n_obs, mean = 0, sd = 0.25)

  # full data structure
  data <- as.data.table(cbind(Y, Z, A, W))
  setnames(data, c("Y", "Z", "A", "W"))
  return(data)
}

# set seed and simulate example data
set.seed(75681)
example_data <- make_mediation_data(100)
node_list <- list(W = "W", A = "A", Z = "Z", Y = "Y")

# consider an incremental propensity score intervention that triples (i.e.,
# delta = 3) the individual-specific odds of receiving treatment
delta_ipsi <- 3

# Added learners
learners <- list(
  Lrnr_glm$new(),    
  Lrnr_bayesglm$new(),             
  Lrnr_ranger$new()  
)

dense_learners <- Lrnr_sl$new(
  learners = learners,
  metalearner = Lrnr_nnls$new()
)

cv_learner <- Lrnr_cv$new(dense_learners, full_fit = TRUE)

learner_list <- list(
  Y = cv_learner, 
  A = cv_learner, 
  Z = cv_learner,
  W = cv_learner
)

# Code that works:
tmle_spec <- tmle_medshift(
  delta = delta_ipsi,
  e_learners = cv_learner,
  phi_learners = cv_learner,
  max_iter = 5
)

# total effect works:
total_out <- tmle3(
  tmle_spec = tmle_spec, 
  data = example_data,
  node_list =  node_list,
  learner_list = learner_list
  )

# Natural direct effect
tmle_spec_NDE <- tmle_NDE(
  e_learners = cv_learner, 
  psi_Z_learners = cv_learner, 
  max_iter = 5
)

# Returns error `Error: Couldn't find W`
NDE_out <- tmle3(
  tmle_spec = tmle_spec_NDE, 
  data = example_data,
  node_list =  node_list,
  learner_list = learner_list
  )

# Same error with Natural indirect effect
tmle_spec_NIE <- tmle_NIE(e_learners = e_learners, psi_Z_learners = phi_learners, max_iter = 5)
NIE_out <- tmle3(
  tmle_spec = tmle_spec_NDE, 
  data = example_data,
  node_list =  node_list,
  learner_list = learner_list
  )

The error message is also very uninformative, I have no idea if this has to do with a mismatch with the node_list and the example_data or because the learner_list doesn't contain an list element W.

Thank you for your time.