Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/236784 
Year of Publication: 
2020
Citation: 
[Journal:] Statistics in Transition New Series [ISSN:] 2450-0291 [Volume:] 21 [Issue:] 4 [Publisher:] Exeley [Place:] New York [Year:] 2020 [Pages:] 123-143
Publisher: 
Exeley, New York
Abstract: 
We develop a technique for record linkage on high dimensional data, where the two datasets may not have any common variable, and there may be no training set available. Our methodology is based on sparse, high dimensional principal components. Since large and high dimensional datasets are often prone to outliers and aberrant observations, we propose a technique for estimating robust, high dimensional principal components. We present theoretical results validating the robust, high dimensional principal component estimation steps, and justifying their use for record linkage. Some numeric results and remarks are also presented.
Subjects: 
record linkage
principal components
high dimensional
robust
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.