Doubly robust inference when combining probability and non-probability samples with high dimensional data.

TitleDoubly robust inference when combining probability and non-probability samples with high dimensional data.
Publication TypeJournal Article
Year of Publication2020
AuthorsYang, Shu, Jae Kwang Kim, and Rui Song
JournalJ R Stat Soc Series B Stat Methodol
Volume82
Issue2
Pagination445-465
Date Published2020 Apr
ISSN1369-7412
Abstract

We consider integrating a non-probability sample with a probability sample which provides high dimensional representative covariate information of the target population. We propose a two-step approach for variable selection and finite population inference. In the first step, we use penalized estimating equations with folded concave penalties to select important variables and show selection consistency for general samples. In the second step, we focus on a doubly robust estimator of the finite population mean and re-estimate the nuisance model parameters by minimizing the asymptotic squared bias of the doubly robust estimator. This estimating strategy mitigates the possible first-step selection error and renders the doubly robust estimator root consistent if either the sampling probability or the outcome model is correctly specified.

DOI10.1111/rssb.12354
Alternate JournalJ R Stat Soc Series B Stat Methodol
Original PublicationDoubly robust inference when combining probability and non-probability samples with high dimensional data.
PubMed ID33162780
PubMed Central IDPMC7644042
Grant ListP01 CA142538 / CA / NCI NIH HHS / United States