2000 character limit reached
Quantile balancing inverse probability weighting for non-probability samples
Published 12 Mar 2024 in stat.ME and stat.AP | (2403.09726v4)
Abstract: The use of non-probability data sources for statistical purposes and for official statistics has become increasingly popular in recent years. However, statistical inference based on non-probability samples is made more difficult by nature of their biasedness and lack of representativity. In this paper we propose quantile balancing inverse probability weighting estimator (QBIPW) for non-probability samples. We apply the idea of Harms and Duchesne (2006) allowing the use of quantile information in the estimation process to reproduce known totals and the distribution of auxiliary variables. We discuss the estimation of the QBIPW probabilities and its variance. Our simulation study has demonstrated that the proposed estimators are robust against model mis-specification and, as a result, help to reduce bias and mean squared error. Finally, we applied the proposed methods to estimate the share of job vacancies aimed at Ukrainian workers in Poland using an integrated set of administrative and survey data about job vacancies.
- Chunrong Ai, Oliver Linton and Zheng Zhang “A Simple and Efficient Estimation Method for Models with Nonignorable Missing Data” In Statistica Sinica 30, 2020, pp. 1949–1970 DOI: 10.5705/ss.202018.0107
- Jean-Francois Beaumont “Are probability surveys bound to disappear for the production of official statistics” In Survey Methodology 46.1 Statistics Canada, 2020, pp. 1–28
- Maciej Beręsewicz “A two-step procedure to measure representativeness of internet data sources” In International Statistical Review 85.3 Wiley Online Library, 2017, pp. 473–493
- Maciej Beręsewicz “jointCalib: A Joint Calibration of Totals and Quantiles” R package version 0.1.0, 2023 URL: https://CRAN.R-project.org/package=jointCalib
- Jack Chen, Richard Valliant and Michael Elliott “Model-assisted calibration of non-probability sample survey data using adaptive LASSO” In Survey Methodology 44.1, 2018, pp. 117–144
- Jack Chen, Richard Valliant and Michael Elliott “Calibrating non-probability surveys to estimated control totals using LASSO, with an application to political polling” In Journal of the Royal Statistical Society: Series C (Applied Statistics) 68.3, 2019, pp. 657–681 DOI: 10.1111/rssc.12327
- Jack Kuang Tsung Chen, Richard L Valliant and Michael R Elliott “Calibrating non-probability surveys to estimated control totals using LASSO, with an application to political polling” In Journal of the Royal Statistical Society Series C: Applied Statistics 68.3 Oxford University Press, 2019, pp. 657–681
- “Approaches to Improving Survey-Weighted Estimates” In Statistical Science 32.2 Institute of Mathematical Statistics, 2017, pp. 227–248 URL: http://www.jstor.org/stable/26408227
- Sixia Chen, Shu Yang and Jae Kwang Kim “Nonparametric Mass Imputation for Data Integration” In Journal of Survey Statistics and Methodology 10.1, 2022, pp. 1–24 DOI: 10.1093/jssam/smaa036
- Yilin Chen, Pengfei Li and Changbao Wu “Doubly robust inference with nonprobability survey samples” In Journal of the American Statistical Association 115.532 Taylor & Francis, 2020, pp. 2011–2021
- Yilin Chen, Pengfei Li and Changbao Wu “Dealing with undercoverage for non-probability survey samples” In Survey Methodology 49.2, 2023, pp. 497–515
- “nonprobsvy: Package for Inference Based on Non-Probability Samples” R package version 0.1.0, https://ncn-foreigners.github.io/nonprobsvy/, 2024 URL: https://github.com/ncn-foreigners/nonprobsvy
- Constance F Citro “From multiple modes for surveys to multiple data sources for estimates” In Survey Methodology 40.2 Statistics Canada, 2014, pp. 137–162
- “Big data as a source for official statistics” In Journal of Official Statistics 31.2 SAGE Publications Sage UK: London, England, 2015, pp. 249–262
- John E Dennis Jr and Robert B Schnabel “Numerical methods for unconstrained optimization and nonlinear equations” SIAM, 1996
- “Calibration estimators in survey sampling” In Journal of the American Statistical Association 87.418 Taylor & Francis, 1992, pp. 376–382
- “The war in Ukraine and migration to Poland: Outlook and challenges” In Intereconomics 57.3 Springer, 2022, pp. 164–170
- Michael R. Elliott and Richard Valliant “Inference for Nonprobability Samples” In Statistical Science 32.2, 2017 DOI: 10.1214/16-STS598
- Andrew Gelman “Poststratification into many categories using hierarchical logistic regression” In Survey Methodology 23, 1997, pp. 127
- “On calibration estimation for quantiles” In Survey Methodology 32.1, 2006, pp. 37–52
- Berend Hasselman “nleqslv: Solve Systems of Nonlinear Equations” R package version 3.3.5, 2023 URL: https://CRAN.R-project.org/package=nleqslv
- Chad Hazlett “Kernel Balancing: A Flexible Non-Parametric Weighting Procedure for Estimating Causal Effects” In SSRN Electronic Journal 30.3, 2020 DOI: 10.2139/ssrn.2746753
- “Covariate Balancing Propensity Score” In Journal of the Royal Statistical Society Series B: Statistical Methodology 76.1, 2014, pp. 243–263 DOI: 10.1111/rssb.12027
- “Combining Non-Probability and Probability Survey Samples Through Mass Imputation” In Journal of the Royal Statistical Society Series A: Statistics in Society 184.3, 2021, pp. 941–963 DOI: 10.1111/rssa.12696
- Jae Kwang Kim and Minsun Kim Riddles “Some theory for propensity-score-adjustment estimators in survey sampling” In Survey Methodology 38.2, 2012, pp. 157–165
- “Sampling techniques for big data analysis” In International Statistical Review 87 Wiley Online Library, 2019, pp. S177–S191
- Giampiero Marra and Simon N Wood “Practical variable selection for generalized additive models” In Computational Statistics & Data Analysis 55.7 Elsevier, 2011, pp. 2372–2387
- Seho Park, Jae Kwang Kim and Kimin Kim “A note on propensity score weighting method using paradata in survey sampling” In Survey Methodology 45.3, 2019, pp. 451–463
- R Core Team “R: A Language and Environment for Statistical Computing”, 2023 R Foundation for Statistical Computing URL: https://www.R-project.org/
- Camilla Salvatore “Inference with non-probability samples and survey data integration: a science mapping study” In Metron Springer, 2023, pp. 1–25
- Pedro H C Sant’Anna, Xiaojun Song and Qi Xu “Covariate Distribution Balance via Propensity Scores” In Journal of Applied Econometrics 37.6, 2022, pp. 1093–1120
- Carl-Erik Särndal “The calibration approach in survey theory and practice” In Survey methodology 33.2, 2007, pp. 99–119
- Statistics Poland “Methodological report The demand for labour”, 2021 URL: https://stat.gov.pl/obszary-tematyczne/rynek-pracy/popyt-na-prace/zeszyt-metodologiczny-popyt-na-prace,3,1.html
- Statistics Poland “Residents of Ukraine under temporary protection”, 2023 URL: https://stat.gov.pl/en/topics/population/internationa-migration/residents-of-ukraine-under-temporary-protection,9,1.html
- “Model-assisted calibration of non-probability sample survey data using adaptive LASSO.” In Survey Methodology 44.1 Statistics Canada, 2018, pp. 117–145
- Changbao Wu “Statistical inference with non-probability survey samples” In Survey Methodology 48, 2022, pp. 283–311
- Changbao Wu and Mary E Thompson “Sampling theory and practice” Springer, 2020
- Shu Yang, Jae Kwang Kim and Rui Song “Doubly Robust Inference when Combining Probability and Non-Probability Samples with High Dimensional Data” In Journal of the Royal Statistical Society Series B: Statistical Methodology 82.2, 2020, pp. 445–465 DOI: 10.1111/rssb.12354
- Shu Yang, Jae-Kwang Kim and Youngdeok Hwang “Integration of data from probability surveys and big found data for finite population inference using mass imputation” In Survey Methodology 47, 2021, pp. 29–58
Paper Prompts
Sign up for free to create and run prompts on this paper.
