File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A Note On Distributed Quantile Regression By Pilot Sampling And One-step Updating

TitleA Note On Distributed Quantile Regression By Pilot Sampling And One-step Updating
Authors
Issue Date2022
Citation
Journal of Business & Economic Statistics, 2022, v. 40, p. 1691-1700 How to Cite?
AbstractQuantile regression is amethod of fundamental importance. Howto efficiently conduct quantile regression for a large dataset on a distributed systemis of great importance.We showthat the popularly used one-shot estimation is statistically inefficient if data are not randomly distributed across different workers. To fix the problem, a novel one-step estimation method is developed with the following nice properties. First, the algorithm is communication efficient. That is the communication cost demanded is practically acceptable. Second, the resulting estimator is statistically efficient. That is its asymptotic covariance is the same as that of the global estimator. Third, the estimator is robust against data distribution. That is its consistency is guaranteed even if data are not randomly distributed across different workers. Numerical experiments are provided to corroborate our findings. A real example is also presented for illustration.
Persistent Identifierhttp://hdl.handle.net/10722/320303

 

DC FieldValueLanguage
dc.contributor.authorPan, R-
dc.contributor.authorRen, T-
dc.contributor.authorGuo, B-
dc.contributor.authorLi, F-
dc.contributor.authorLi, G-
dc.contributor.authorWang, H-
dc.date.accessioned2022-10-21T07:50:47Z-
dc.date.available2022-10-21T07:50:47Z-
dc.date.issued2022-
dc.identifier.citationJournal of Business & Economic Statistics, 2022, v. 40, p. 1691-1700-
dc.identifier.urihttp://hdl.handle.net/10722/320303-
dc.description.abstractQuantile regression is amethod of fundamental importance. Howto efficiently conduct quantile regression for a large dataset on a distributed systemis of great importance.We showthat the popularly used one-shot estimation is statistically inefficient if data are not randomly distributed across different workers. To fix the problem, a novel one-step estimation method is developed with the following nice properties. First, the algorithm is communication efficient. That is the communication cost demanded is practically acceptable. Second, the resulting estimator is statistically efficient. That is its asymptotic covariance is the same as that of the global estimator. Third, the estimator is robust against data distribution. That is its consistency is guaranteed even if data are not randomly distributed across different workers. Numerical experiments are provided to corroborate our findings. A real example is also presented for illustration.-
dc.languageeng-
dc.relation.ispartofJournal of Business & Economic Statistics-
dc.titleA Note On Distributed Quantile Regression By Pilot Sampling And One-step Updating-
dc.typeArticle-
dc.identifier.emailLi, G: gdli@hku.hk-
dc.identifier.authorityLi, G=rp00738-
dc.identifier.doi10.1080/07350015.2021.1961789-
dc.identifier.hkuros339980-
dc.identifier.volume40-
dc.identifier.spage1691-
dc.identifier.epage1700-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats