Łukasz Chrostowski | Searcharxiv

arXiv2026

Data integration of non-probability and probability samples with deterministic predictive mean matching

We study deterministic predictive mean matching mass imputation estimators to integrate data from probability and non-probability samples. We consider two approaches: predicted-to-predicted (PMM~A) and predicted-to-observed (PMM~B) matching. We prove the consistency of mean estimators, derive a variance decomposition, and propose estimators of variance. We establish consistency of the PMM~A estimator under model misspecification and underline key differences from the nearest neighbour method. Our PMM~B approach can be employed with non-parametric regression techniques, such as kernel regression, and the analytical expression for variance applies to nearest neighbour matching for non-probability samples. Extensive simulation studies compare properties of the proposed estimators with existing alternatives and examine the effects of model misspecification. The paper concludes with an empirical study on the integration of job vacancy survey and vacancies submitted to public employment offices (admin and online data). Open-source software is available.

stat.ME↗

arXiv2025

nonprobsvy -- An R package for modern methods for non-probability surveys

The following paper presents nonprobsvy -- an R package for inference based on non-probability samples. The package implements various approaches that can be categorized into three groups: prediction-based approach, inverse probability weighting and doubly robust approach. In the package, we assume the existence of either population-level data or probability-based population information and leverage the survey package for inference. The package implements both analytical and bootstrap variance estimation for the proposed estimators. In the paper we present the theory behind the package, its functionalities and case study that showcases the usage of the package. The package is aimed at scientists and researchers who would like to use non-probability samples (e.g.big data, opt-in web panels, social media) to accurately estimate population characteristics.

stat.ME↗