Thresholding Nonprobability Units in Combined Data for Efficient Domain Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Savitsky, Terrance D., Williams, Matthew R., Gerrshunskaya, Julie, Beresovsky, Vladislav
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929714218663936
author Savitsky, Terrance D.
Williams, Matthew R.
Gerrshunskaya, Julie
Beresovsky, Vladislav
author_facet Savitsky, Terrance D.
Williams, Matthew R.
Gerrshunskaya, Julie
Beresovsky, Vladislav
contents Quasi-randomization approaches estimate latent participation probabilities for units from a nonprobability / convenience sample. Estimation of participation probabilities for convenience units allows their combination with units from the randomized survey sample to form a survey weighted domain estimate. One leverages convenience units for domain estimation under the expectation that estimation precision and bias will improve relative to solely using the survey sample; however, convenience sample units that are very different in their covariate support from the survey sample units may inflate estimation bias or variance. This paper develops a method to threshold or exclude convenience units to minimize the variance of the resulting survey weighted domain estimator. We compare our thresholding method with other thresholding constructions in a simulation study for two classes of datasets based on degree of overlap between survey and convenience samples on covariate support. We reveal that excluding convenience units that each express a low probability of appearing in \emph{both} reference and convenience samples reduces estimation error.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09524
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thresholding Nonprobability Units in Combined Data for Efficient Domain Estimation
Savitsky, Terrance D.
Williams, Matthew R.
Gerrshunskaya, Julie
Beresovsky, Vladislav
Methodology
Quasi-randomization approaches estimate latent participation probabilities for units from a nonprobability / convenience sample. Estimation of participation probabilities for convenience units allows their combination with units from the randomized survey sample to form a survey weighted domain estimate. One leverages convenience units for domain estimation under the expectation that estimation precision and bias will improve relative to solely using the survey sample; however, convenience sample units that are very different in their covariate support from the survey sample units may inflate estimation bias or variance. This paper develops a method to threshold or exclude convenience units to minimize the variance of the resulting survey weighted domain estimator. We compare our thresholding method with other thresholding constructions in a simulation study for two classes of datasets based on degree of overlap between survey and convenience samples on covariate support. We reveal that excluding convenience units that each express a low probability of appearing in \emph{both} reference and convenience samples reduces estimation error.
title Thresholding Nonprobability Units in Combined Data for Efficient Domain Estimation
topic Methodology
url https://arxiv.org/abs/2502.09524