Generalized regression estimators with concave penalties and a comparison to lasso type estimators

Elena McDonald () and Xin Wang ()
Additional contact information
Elena McDonald: Archer Daniels Midland
Xin Wang: San Diego State University

METRON, 2024, vol. 82, issue 2, No 5, 213-239

Abstract: Abstract The generalized regression (GREG) estimator is usually used in survey sampling when incorporating auxiliary information. Generally, not all available covariates significantly contribute to the estimation process when there are multiple covariates. We propose two new GREG estimators based on concave penalties: one built from the smoothly clipped absolute deviation (SCAD) penalty and the other built from the minimax concave penalty (MCP). The performances of these estimators are compared to lasso-type estimators through a simulation study in a simple random sample (SRS) setting and a probability proportional to size (PPS) sample setting. It is shown that the proposed estimators produce improved estimates of the population total compared to that of the traditional GREG estimator and the estimators built from LASSO. Asymptotic properties are also derived for the proposed estimators. Bootstrap methods are also explored to improve coverage probability when the sample size is small.

Keywords: Auxiliary information; Concave penalties; Generalized regression estimation; MCP; Model-assisted; SCAD; Survey sampling (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s40300-023-00253-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:metron:v:82:y:2024:i:2:d:10.1007_s40300-023-00253-4

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/40300

DOI: 10.1007/s40300-023-00253-4

Access Statistics for this article

METRON is currently edited by Marco Alfo'

More articles in METRON from Springer, Sapienza Università di Roma
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().