The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

weightflow: Declarative Recipes for Staged Survey Weighting with Recipe-Aware Replicate Variances

Builds survey analysis weights by declaring the whole weighting process as an ordered recipe of explicit adjustments and estimating it in a single call. The recipe follows the stages of a real household survey: redistribution of unresolved eligibility, within-household selection, nonresponse adjustment by weighting classes, by response-propensity models (logistic regression or machine-learning learners such as trees, random forests and gradient boosting, with optional cross-fitting) or by two-phase calibration for nonresponse, calibration to known population totals following Deville and Sarndal (1992) <doi:10.2307/2290268>, optional model-assisted (model) calibration to auxiliary predictions following Wu and Sitter (2001) <doi:10.1198/016214501750333054>, and range-restricted trimming that bounds the weights while preserving the calibration totals. Variances come from a recipe-aware bootstrap and jackknife that resample or delete primary sampling units and re-apply the entire cascade on each replicate, following the rescaling bootstrap of Rao and Wu (1988) <doi:10.1080/01621459.1988.10478591>, so the replicate weights carry the variability of every adjustment instead of treating the adjustments as known. A self-contained HTML report documents each step with its diagnostics, and the weights bridge to the 'survey' and 'srvyr' packages for design-based inference.

Version: 1.1.0
Depends: R (≥ 4.1.0)
Imports: stats, utils, graphics, parallel
Suggests: MASS, rpart, ranger, testthat (≥ 3.0.0), survey, srvyr, dplyr, tidyr, ggplot2, haven, archive, knitr, rmarkdown, spelling, xgboost
Published: 2026-08-19
DOI: 10.32614/CRAN.package.weightflow
Author: Juan Pablo Ferreira ORCID iD [aut, cre], Andrés Gutiérrez ORCID iD [aut]
Maintainer: Juan Pablo Ferreira <juanpablo.ferreira at fcea.edu.uy>
BugReports: https://github.com/jpferreira33/weightflow/issues
License: MIT + file LICENSE
URL: https://github.com/jpferreira33/weightflow, https://jpferreira33.github.io/weightflow/
NeedsCompilation: no
Language: en-US
Citation: weightflow citation info
Materials: README, NEWS
In views: OfficialStatistics
CRAN checks: weightflow results

Documentation:

Reference manual: weightflow.html , weightflow.pdf
Vignettes: Machine learning, cross-fitting and robust calibration (source, R code)
Ways to specify calibration totals (source, R code)
Calibration: raking, post-stratification and GREG (source, R code)
Model calibration (model-assisted weighting) (source, R code)
Nonresponse: weighting classes, propensities and calibration (source, R code)
Preparing the sample: eligibility and response before weighting (source, R code)
Documenting and auditing the weights: the quality report (source, R code)
From raw sample to final weights (source, R code)
Trimming survey weights (source, R code)
Validation against the survey package (source, R code)
Variance estimation (source, R code)
Staged survey weighting: the adjustment logic (source, R code)

Downloads:

Package source: weightflow_1.1.0.tar.gz
Windows binaries: r-devel: weightflow_1.0.0.zip, r-release: weightflow_1.1.0.zip, r-oldrel: weightflow_1.1.0.zip
macOS binaries: r-release (arm64): weightflow_1.1.0.tgz, r-oldrel (arm64): weightflow_1.1.0.tgz, r-release (x86_64): weightflow_1.1.0.tgz, r-oldrel (x86_64): weightflow_1.1.0.tgz
Old sources: weightflow archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=weightflow to link to this page.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.