Design-unbiased statistical learning in survey sampling
Design-unbiased statistical learning in survey sampling
Design-consistent model-assisted estimation has become the standard practice in survey sampling. However, design consistency remains to be established for many machine-learning techniques that can potentially be very powerful assisting models. We propose a subsampling Rao-Blackwell method, and develop a statistical learning theory for exactly design-unbiased estimation with the help of linear or non-linear prediction models. Our approach makes use of classic ideas from Statistical Science as well as the rapidly growing field of Machine Learning. Provided rich auxiliary information, it can yield considerable efficiency gains over standard linear model-assisted methods, while en- suring valid estimation for the given target population, which is robust against potential mis-specifications of the assisting model, even if the design consistency of following the standard recipe for plug-in model-assisted estimator cannot be established.
Rao-Blackwellisation, bagging, pq-unbiasedness, stability conditions
Sanguiao Sande, Luis
b7fb02e4-7b94-488a-85aa-e8f2a25fce70
Zhang, Li-Chun
a5d48518-7f71-4ed9-bdcb-6585c2da3649
Sanguiao Sande, Luis
b7fb02e4-7b94-488a-85aa-e8f2a25fce70
Zhang, Li-Chun
a5d48518-7f71-4ed9-bdcb-6585c2da3649
Sanguiao Sande, Luis and Zhang, Li-Chun
(2020)
Design-unbiased statistical learning in survey sampling.
Sankhya: The Indian Journal of Statistics.
(doi:10.1007/s13171-020-00224-1).
Abstract
Design-consistent model-assisted estimation has become the standard practice in survey sampling. However, design consistency remains to be established for many machine-learning techniques that can potentially be very powerful assisting models. We propose a subsampling Rao-Blackwell method, and develop a statistical learning theory for exactly design-unbiased estimation with the help of linear or non-linear prediction models. Our approach makes use of classic ideas from Statistical Science as well as the rapidly growing field of Machine Learning. Provided rich auxiliary information, it can yield considerable efficiency gains over standard linear model-assisted methods, while en- suring valid estimation for the given target population, which is robust against potential mis-specifications of the assisting model, even if the design consistency of following the standard recipe for plug-in model-assisted estimator cannot be established.
Text
SL
- Accepted Manuscript
More information
Accepted/In Press date: 20 September 2020
e-pub ahead of print date: 6 October 2020
Additional Information:
Publisher Copyright:
© 2020, Indian Statistical Institute.
Keywords:
Rao-Blackwellisation, bagging, pq-unbiasedness, stability conditions
Identifiers
Local EPrints ID: 444553
URI: http://eprints.soton.ac.uk/id/eprint/444553
ISSN: 0581-5738
PURE UUID: 1b66ca50-d72c-417d-80ec-8f7f54634568
Catalogue record
Date deposited: 23 Oct 2020 16:33
Last modified: 17 Mar 2024 05:57
Export record
Altmetrics
Contributors
Author:
Luis Sanguiao Sande
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
