Package: NMAR 0.1.2

Maciej Beresewicz

NMAR: Estimation under not Missing at Random Nonresponse

Methods to estimate finite-population parameters under nonresponse that is not missing at random (NMAR, nonignorable). Incorporates auxiliary information and user-specified response models, and supports independent samples and complex survey designs via objects from the 'survey' package. Provides diagnostics and optional variance estimates. For methodological background see Qin, Leung and Shao (2002) <doi:10.1198/016214502753479338> and Riddles, Kim and Im (2016) <doi:10.1093/jssam/smv047>.

Authors:Maciej Beresewicz [aut, cre], Igor Kołodziej [aut, ctb], Mateusz Iwaniuk [aut, ctb]

NMAR_0.1.2.tar.gz
NMAR_0.1.2.zip(r-4.7)NMAR_0.1.2.zip(r-4.6)NMAR_0.1.2.zip(r-4.5)
NMAR_0.1.2.tgz(r-4.6-any)NMAR_0.1.2.tgz(r-4.5-any)
NMAR_0.1.2.tar.gz(r-4.7-any)NMAR_0.1.2.tar.gz(r-4.6-any)
NMAR_0.1.2.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
NMAR/json (API)

# Install 'NMAR' in R:
install.packages('NMAR', repos = c('https://ncn-foreigners.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/ncn-foreigners/nmar/issues

Datasets:

On CRAN:

Conda:

missing-datanon-ignorableselection-biassurvey

5.60 score 4 stars 8 scripts 96 downloads 7 exports 3 dependencies

Last updated from:f9e5de913a. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK153
source / vignettesOK180
linux-release-x86_64OK138
macos-release-arm64OK110
macos-oldrel-arm64OK94
windows-develOK137
windows-releaseOK101
windows-oldrelOK104
wasm-releaseOK116

Exports:el_engineengine_configengine_nameexptilt_engineexptilt_nonparam_enginenmarse

Dependencies:Formulagenericsnleqslv

Empirical Likelihood
Overview | Quick start | Data-frame example | Respondents-only data | Response-only predictors | Survey design example | Practical guidance | Solver control and notes | References and further reading
Rendered fromtutorial_empirical_likelihood.Rmdusingknitr::rmarkdown

Last update: 2026-02-04
Started: 2025-12-10

Exponential Tilting Theory
Overview | Notation and main objects | The vectorized score S_2 and matrix algebra | Mean estimation and survey weights | Arguments passed to exptilt (summary) | Connection to the EM viewpoint | Stopping criterion (maximum-norm) | Practical tutorial: from raw data to matrix operations (conceptual steps) | Why the vectorization matters (practical remarks) | Closing notes and references
Rendered fromexptilt_theory.Rmdusingknitr::rmarkdown

Last update: 2025-12-18
Started: 2025-12-10

Exponential Tilting
Overview | Input data | Required Structure | Engine Configuration | Results | Survey designs
Rendered fromtutorial_exptilt.Rmdusingknitr::rmarkdown

Last update: 2025-12-18
Started: 2025-12-10

Exponential Tilting (Nonparametric)
Overview | Input Data | Required Structure: | Engine Configuration | Results | Survey designs
Rendered fromtutorial_exptilt_nonparam.Rmdusingknitr::rmarkdown

Last update: 2025-12-18
Started: 2025-12-10

Nonparametric Exponential Tilting Theory
Overview | Notation and Main Objects | Fixed Objects (Pre-computed) | Iterative Objects (The EM Algorithm) | The Expectation-Maximization (EM) Algorithm | Step 1.1 (E-Step): Compute Expected Nonrespondent Counts | Step 1.2 (M-Step): Update Odds Matrix | Step 2: Convergence | Final Estimates and Survey Weights | Survey Weights | Final Adjusted Counts | Final Proportion $\hat{\theta}_j$
Rendered fromexptilt_nonparam_theory.Rmdusingknitr::rmarkdown

Last update: 2025-12-10
Started: 2025-12-10

Readme and manuals

Help Manual

Help pageTopics
Default coefficients for NMAR resultscoef.nmar_result
Coefficient table for summary objectscoef.summary_nmar_result
Wald confidence interval for NMAR resultsconfint.nmar_result
Confidence intervals for summary objectsconfint.summary_nmar_result
Empirical likelihood engine for NMARel_engine
Extract engine configurationengine_config
Canonical engine nameengine_name
Exponential tilting engine for NMARexptilt_engine
Nonparametric exponential tilting engine for NMARexptilt_nonparam_engine
Default fitted values for NMAR resultsfitted.nmar_result
Formatter for enginesformat.nmar_engine
Default formula for NMAR resultsformula.nmar_result
Glance summary for NMAR resultsglance.nmar_result
Not Missing at Random Estimationnmar
Polish Household Budget Data with Simulated Nonignorable Nonresponsepolish_households
Print method for enginesprint.nmar_engine
Print method for nmar_resultprint.nmar_result
Print method for EL resultsprint.nmar_result_el
Print method for Exponential Tilting results (engine-specific)print.nmar_result_exptilt
Print method for summary.nmar_resultprint.summary_nmar_result
Riddles Simulation, Case 1: Linear Meanriddles_case1
Riddles Simulation, Case 2: Exponential Meanriddles_case2
Riddles Simulation, Case 3: Sine Wave Meanriddles_case3
Riddles Simulation, Case 4: Cubic Meanriddles_case4
Extract standard error for NMAR resultsse
Summary method for nmar_resultsummary.nmar_result
Summary method for EL resultssummary.nmar_result_el
Summary method for Exponential Tilting results (engine-specific)summary.nmar_result_exptilt
Tidy summary for NMAR resultstidy.nmar_result
Variance-covariance for NMAR resultsvcov.nmar_result
Aggregated Exit Poll Data for Gangdong-Gap (2012)voting
Extract weights from an `nmar_result`weights.nmar_result