Title:	Multiple Imputation by Super Learning
Version:	2.0.0
Description:	Performs multiple imputation of missing data using an ensemble super learner built with the tidymodels framework. For each incomplete column, a stacked ensemble of candidate learners is trained on a bootstrap sample of the observed data and used to generate imputations via predictive mean matching (continuous), probability draws (binary), or cumulative probability draws (categorical). Supports parallelism across imputed datasets via the future framework.
License:	MIT + file LICENSE
URL:	https://github.com/JustinManjourides/misl
BugReports:	https://github.com/JustinManjourides/misl/issues
Encoding:	UTF-8
RoxygenNote:	7.3.3
Depends:	R (≥ 4.1.0)
Imports:	dplyr (≥ 1.1.0), future.apply (≥ 1.11.0), parsnip (≥ 1.2.0), recipes (≥ 1.0.0), rsample (≥ 1.2.0), stacks (≥ 1.0.0), stats, tibble (≥ 3.2.0), tidyr (≥ 1.3.0), tune (≥ 1.2.0), utils, workflows (≥ 1.1.0)
Suggests:	earth (≥ 5.3.0), future (≥ 1.33.0), ggforce, ggplot2, knitr, MASS, ranger (≥ 0.16.0), rmarkdown, scales, testthat (≥ 3.0.0), xgboost (≥ 1.7.0)
VignetteBuilder:	knitr
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2026-04-08 00:02:45 UTC; j.manjourides
Author:	Justin Manjourides [aut, cre], Thomas Carpenito [aut]
Maintainer:	Justin Manjourides <j.manjourides@northeastern.edu>
Repository:	CRAN
Date/Publication:	2026-04-08 05:00:02 UTC

Fit a stacked super learner ensemble

Description

Fit a stacked super learner ensemble

Usage

.fit_super_learner(
  train_data,
  full_data,
  xvars,
  yvar,
  outcome_type,
  learner_names,
  cv_folds = 5
)

Arguments

Value

Named list with $boot (fit on bootstrap sample) and $full (fit on full observed data; NULL unless continuous).

Validate the input dataset before imputation

Description

Validate the input dataset before imputation

Usage

check_dataset(dataset)

Arguments

Determine the outcome type of a column

Description

Determine the outcome type of a column

Usage

check_datatype(x)

Arguments

Value

One of "categorical", "ordinal", "binomial", or "continuous".

List available learners for MISL imputation

Description

Displays the built-in named learners available for use in misl(). Note that any parsnip-compatible model spec can also be passed directly via the *_method arguments.

Usage

list_learners(outcome_type = "all", installed_only = FALSE)

Arguments

Value

A tibble with columns learner, description, package, installed, and outcome-type support flags (when outcome_type = "all").

Examples

list_learners()
list_learners("continuous")
list_learners("ordinal")
list_learners("categorical", installed_only = TRUE)

MISL: Multiple Imputation by Super Learning (v2.0)

Description

Imputes missing values using multiple imputation by super learning.

Usage

misl(
  dataset,
  m = 5,
  maxit = 5,
  seed = NA,
  con_method = c("glm", "rand_forest", "boost_tree"),
  bin_method = c("glm", "rand_forest", "boost_tree"),
  cat_method = c("rand_forest", "boost_tree"),
  ord_method = c("polr", "rand_forest", "boost_tree"),
  cv_folds = 5,
  ignore_predictors = NA,
  quiet = TRUE
)

Arguments

Details

Built-in named learners (see list_learners()):

• "glm" - base R (logistic for binary, linear for continuous)

• "rand_forest" - ranger

• "boost_tree" - xgboost

• "mars" - earth

• "multinom_reg" - nnet (unordered categorical only)

• "polr" - MASS (ordered categorical only)

Any parsnip-compatible model spec can also be passed directly via the *_method arguments. Named strings and parsnip specs can be mixed in the same list:

library(parsnip)
misl(data,
  con_method = list(
    "glm",
    rand_forest(trees = 500) |> set_engine("ranger")
  )
)

The mode (regression vs classification) is always enforced by misl regardless of what is set on the spec.

Value

A list of m named lists, each with:

datasets

A fully imputed tibble.

trace

A long-format tibble of mean/sd trace statistics per iteration, for convergence inspection.

Parallelism

Imputation across the m datasets is parallelised via future.apply. To enable parallel execution, set a future plan before calling misl():

library(future)
plan(multisession, workers = 4)
result <- misl(data, m = 5)
plan(sequential)

Examples

# Using named learners (same as v1.0)
set.seed(1)
n <- 100
demo_data <- data.frame(x1 = rnorm(n), x2 = rnorm(n), y = rnorm(n))
demo_data[sample(n, 10), "y"] <- NA
misl_imp <- misl(demo_data, m = 2, maxit = 2, con_method = "glm")

# Using a custom parsnip spec
## Not run: 
library(parsnip)
misl_imp <- misl(
  demo_data, m = 2, maxit = 2,
  con_method = list(
    "glm",
    rand_forest(trees = 500) |> set_engine("ranger")
  )
)

## End(Not run)

Plot trace statistics from a MISL imputation

Description

Plots the mean and standard deviation of imputed values across iterations for all incomplete variables, paginated in grids of up to 3 variables per page. Stable traces that mix well across datasets indicate convergence. Note that trace statistics are only computed for continuous and numeric binary columns – categorical and ordinal columns are excluded automatically.

Usage

plot_misl_trace(misl_result, ncol = 2, nrow = 3)

Arguments

Value

Invisibly returns the long-format trace data frame used for plotting.

Examples

set.seed(1)
n <- 100
demo_data <- data.frame(x1 = rnorm(n), x2 = rnorm(n), y = rnorm(n))
demo_data[sample(n, 10), "y"] <- NA
misl_imp <- misl(demo_data, m = 3, maxit = 3, con_method = "glm")
plot_misl_trace(misl_imp)

Predict method for misl_polr_fit objects

Description

Predict method for misl_polr_fit objects

Usage

## S3 method for class 'misl_polr_fit'
predict(object, new_data, type = "prob", ...)