Function to estimate outcome regression as a function of A, C, M1,
and M2
. Because later we will need to marginalize these estimates over
estimated distributions of M1
and M2
, the output includes the predicted
value for each C_i, i = 1, ..., n and for every value of A
in
a_0
. The output is formatted as an n-length list where there is one entry
for each observation. This entry includes a list of predicted values under each treatment
Qbar_a_0
, which is itself a list with a vector of predictions for each value of
a_0
. Also included is an entry called which_M1_obs
, which indicates rows of
the all_mediator_values
that correspond to this observation's observed value of
M1
and M2
. Similarly, there is a vector which_M2_obs
, and also a vector
which_M1_M2_obs
, which indicates the row of all_mediator_values
that
corresponds to this observation's observed value of BOTH M1
and M2
.
estimate_Qbar( Y, A, M1, M2, C, DeltaA, DeltaM, SL_Qbar, glm_Qbar = NULL, a_0, stratify, family, verbose = FALSE, return_models = FALSE, valid_rows, all_mediator_values, ... )
Y | A vector of continuous or binary outcomes. |
---|---|
A | A vector of binary treatment assignment (assumed to be equal to 0 or 1). |
M1 | A |
M2 | A |
C | A |
DeltaA | Indicator of missing treatment (assumed to be equal to 0 if missing 1 if observed). |
DeltaM | Indicator of missing outcome (assumed to be equal to 0 if missing 1 if observed). |
SL_Qbar | A vector of characters or a list describing the Super Learner library to be used for the outcome regression. |
glm_Qbar | A character describing a formula to be used in the call to
|
a_0 | A list of fixed treatment values |
stratify | A |
family | A character passed to |
verbose | A boolean indicating whether to print status updates. |
return_models | A boolean indicating whether to return model fits for the outcome regression, propensity score, and reduced-dimension regressions. |
valid_rows | A |
all_mediator_values | All combinations of M1 and M2 |
... | Additional arguments (not currently used) |