README

NMAR provides estimators for finite-population means when outcomes are subject to nonignorable nonresponse (Not Missing at Random, NMAR). It supports iid data.frame inputs and complex survey designs via survey.design objects from the survey package, and exposes a unified interface through nmar().

Methods

Installation

install.packages("NMAR")

# install.packages("pak")
pak::pak("ncn-foreigners/NMAR")

# install.packages("remotes")
remotes::install_github("ncn-foreigners/NMAR")

remotes::install_github("ncn-foreigners/NMAR", build_vignettes = TRUE)

Usage

Formula interface

nmar() uses a two-sided formula with the outcome on the left-hand side. In the common “missing values indicate nonresponse” workflow, nonrespondents are encoded as NA in the outcome.

Many engines support a partitioned right-hand side via | (e.g., y_miss ~ block1_vars | block2_vars), but the interpretation of these blocks is engine-specific. See ?el_engine and ?exptilt_engine for details.

Example

suppressPackageStartupMessages(library(NMAR))

data("riddles_case1", package = "NMAR")

# Empirical likelihood (EL)
fit_el <- nmar(
  y ~ x,
  data = riddles_case1,
  engine = el_engine(variance_method = "none")
)
summary(fit_el)
#> NMAR Model Summary
#> =================
#> y mean: -1.001986
#> Converged: TRUE 
#> Variance method: none 
#> Variance notes: Variance skipped (variance_method='none') 
#> Total units: 500 
#> Respondents: 368 
#> Call: nmar(y ~ x, data = <data.frame: N=500>, engine = empirical_likelihood)
#> 
#> Missingness-model coefficients:
#>              Estimate
#> (Intercept)  0.860555
#> y           -0.175376

# Exponential tilting (ET)
fit_et <- nmar(
  y ~ x,
  data = riddles_case1,
  engine = exptilt_engine(y_dens = "normal", family = "logit", variance_method = "none")
)
summary(fit_et)
#> NMAR Model Summary (Exponential tilting)
#> =================================
#> y mean: -1.004076
#> Converged: TRUE 
#> Variance method: none 
#> Call: nmar(y ~ x, data = <data.frame: N=?>, engine = exponential_tilting)
#> 
#> Response-model (theta) coefficients:
#>   (Intercept)          : 0.864241
#>   y                    : -0.169948

Result objects returned by nmar() support methods such as summary(), weights(), se(), and confint(), and tidy() / glance() via the generics package.

Survey designs

if (requireNamespace("survey", quietly = TRUE)) {
  suppressPackageStartupMessages(library(survey))
  set.seed(1)
  d <- riddles_case1
  d$w <- runif(nrow(d), 0.5, 2)
  des <- survey::svydesign(ids = ~1, weights = ~w, data = d)

  fit_svy <- nmar(y ~ x, data = des, engine = el_engine(variance_method = "none"))
  summary(fit_svy)
}
#> NMAR Model Summary
#> =================
#> y mean: -1.005961
#> Converged: TRUE 
#> Variance method: none 
#> Variance notes: Variance skipped (variance_method='none') 
#> Total units: 621.7412 
#> Respondents: 368 
#> Call: nmar(y ~ x, data = <survey.design: N=621.741>, engine = empirical_likelihood)
#> 
#> Missingness-model coefficients:
#>              Estimate
#> (Intercept)  0.893453
#> y           -0.129256

Getting help

If you encounter a clear bug, please file an issue with a minimal reproducible example on GitHub

Citation

If you use NMAR in academic work, please cite the package and the relevant method paper(s):

NMAR