Patent Citations: An Examination of the Data Generating Process

35 Pages Posted: 14 Jan 2016 Last revised: 2 Feb 2016

Jeffrey M. Kuhn

University of North Carolina (UNC) at Chapel Hill - Management-Strategy Area

Kenneth A. Younge

École Polytechnique Fédérale de Lausanne (EPFL-CDM)

Date Written: February 1, 2016

Abstract

Existing measures of innovation often rely on patent citations to indicate intellectual lineage and impact. We show that the data generating process for patent citations has changed substantially since citation-based measures were validated a decade ago. Today, far more citations are created per patent, and the mean technological similarity between citing and cited patents has fallen significantly. These changes suggest that the use of patent citations for scholarship needs to be re-validated. We develop a novel vector space model to examine the information content of patent citations, and show that methods for sub-setting and/or weighting informative citations can substantially improve the predictive power of patent citation measures. We make data for a basic correction available for future scholarship through the Patent Research Foundation.

Keywords: patents, citations, rejections

Suggested Citation

Kuhn, Jeffrey M. and Younge, Kenneth A., Patent Citations: An Examination of the Data Generating Process (February 1, 2016). Available at SSRN: https://ssrn.com/abstract=2714954 or http://dx.doi.org/10.2139/ssrn.2714954

Jeffrey M. Kuhn (Contact Author)

University of North Carolina (UNC) at Chapel Hill - Management-Strategy Area ( email )

Chapel Hill, NC 27599
United States

Kenneth A. Younge

École Polytechnique Fédérale de Lausanne (EPFL-CDM) ( email )

Station 5
1015 Lausanne
Switzerland

Paper statistics

Downloads
231
Rank
108,367
Abstract Views
655