Abstract
A method is explained for analysing matrices of statistics where each element should be approximately proportional to some column coefficient and also to some row coefficient. Using U. S. patent data as an example it is shown that entries are usually proportional to country “size” and patent category “size”. Deviations from proportionality expectations when tabulated often suggest policy implications.
This is a preview of subscription content, access via your institution.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
de Solla Price, D. The analysis of scientometric matrices for policy implications. Scientometrics 3, 47–53 (1981). https://doi.org/10.1007/BF02021863
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02021863
Keywords
- Policy Implication
- Patent Data
- Column Coefficient