This class inherits from the
missing_data.frame-class but is customized for the situation
where the sample is a randomized experiment.
fit_model-methods for the experiment_missing_data.frame class take into account the
special nature of a randomized experiment. At the moment, the treatment variable must be binary and
Objects can be created by calls of the form
However, its users almost always will pass a
data.frame to the
missing_data.frame function and specify the
The experiment_missing_data.frame class inherits from the
has two additional slots
Object of class
factor whose length is equal to the number of variables
and whose levels are
Object of class
character of length one, indicating whether the missingness
is in the outcomes only, in the covariates only, or in both the outcomes and covariates. This slot
is filled automatically by the
Ben Goodrich and Jonathan Kropko, for this version, based on earlier versions written by Yu-Sung Su, Masanao Yajima, Maria Grazia Pittau, Jennifer Hill, and Andrew Gelman.
1 2 3 4 5 6 7 8 9 10 11
rdf <- rdata.frame(n_full = 2, n_partial = 2, restrictions = "stratified", experiment = TRUE, types = c("t", "ord", "con", "pos"), treatment_cor = c(0, 0, NA, 0, NA)) Sigma <- tcrossprod(rdf$L) rownames(Sigma) <- colnames(Sigma) <- c("treatment", "X_2", "y_1", "Y_2", "missing_y_1", "missing_Y_2") print(round(Sigma, 3)) concept <- as.factor(c("treatment", "covariate", "covariate", "outcome")) mdf <- missing_data.frame(rdf$obs, subclass = "experiment", concept = concept)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.