nonprobsvy - Inference Based on Non-Probability Samples

Statistical inference with non-probability samples when auxiliary information from external sources such as probability samples or population totals or means is available. The package implements various methods such as inverse probability (propensity score) weighting, mass imputation and doubly robust approach. Details can be found in: Chen et al. (2020) <doi:10.1080/01621459.2019.1677241>, Yang et al. (2020) <doi:10.1111/rssb.12354>, Kim et al. (2021) <doi:10.1111/rssa.12696>, Yang et al. (2021) <https://www150.statcan.gc.ca/n1/pub/12-001-x/2021001/article/00004-eng.htm> and Wu (2022) <https://www150.statcan.gc.ca/n1/pub/12-001-x/2022002/article/00002-eng.htm>.

Last updated 5 days ago

inverse-probability-weightslasso-regressionnonprobability-samplingpropensity-scoressurveyopenblascpp

6.34 score 46 stars 40 scripts 432 downloads

singleRcapture - Single-Source Capture-Recapture Models

Implementation of single-source capture-recapture methods for population size estimation using zero-truncated, zero-one truncated and zero-truncated one-inflated Poisson, Geometric and Negative Binomial regression as well as Zelterman's and Chao's regression. Package includes point and interval estimators for the population size with variances estimated using analytical or bootstrap method. Details can be found in: van der Heijden et all. (2003) <doi:10.1191/1471082X03st057oa>, Böhning and van der Heijden (2019) <doi:10.1214/18-AOAS1232>, Böhning et al. (2020) Capture-Recapture Methods for the Social and Medical Sciences or Böhning and Friedl (2021) <doi:10.1007/s10260-021-00556-8>.

Last updated 2 months ago

6.16 score 11 stars 29 scripts 511 downloads

jointCalib - A Joint Calibration of Totals and Quantiles

A small package containing functions to perform a joint calibration of totals and quantiles. The calibration for totals is based on Deville and Särndal (1992) <doi:10.1080/01621459.1992.10475217>, the calibration for quantiles is based on Harms and Duchesne (2006) <https://www150.statcan.gc.ca/n1/en/catalogue/12-001-X20060019255>. The package uses standard calibration via the 'survey', 'sampling' or 'laeken' packages. In addition, entropy balancing via the 'ebal' package and empirical likelihood based on codes from Wu (2005) <https://www150.statcan.gc.ca/n1/pub/12-001-x/2005002/article/9051-eng.pdf> can be used. See the paper by Beręsewicz and Szymkowiak (2023) for details <arXiv:2308.13281>. The package also includes functions to reweight the control group to the treatment reference distribution and to balance the covariate distribution using the covariate balancing propensity score via the 'CBPS' package for binary treatment observational studies.

Last updated 1 years ago

calibrationcausal-inferenceprobability-samplessamplingsurveysurvey-methodologyweighting

5.00 score 5 stars 8 scripts 180 downloads