This paper uses transaction-based data to provide new insights into the link between the geographic proximity of businesses and associated economic activity. It develops two new measures of, and a set of stylized facts about, the distances between observed transactions between customers and vendors for a research intensive sector. Spending on research inputs is more likely with businesses physically closer to universities than those further away. Firms supplying a university project in one year are more likely to subsequently open an establishment near that university. Vendors who have supplied a project, are subsequently more likely to be a vendor on the same or related project.

We identify two polar life cycles of scholarly creativity among Nobel laureate economists with Tinbergen falling broadly in the middle. Experimental innovators work inductively, accumulating knowledge from experience. Conceptual innovators work deductively, applying abstract principles. Innovators whose work is more conceptual do their most important work earlier in their careers than those whose work is more experimental. Our estimates imply that the probability that the most conceptual laureate publishes his single best work peaks at age 25 compared to the mid-50 s for the most experimental laureate. Thus, while experience benefits experimental innovators, newness to a field benefits conceptual innovators.

In this issue, Kindel et al. describe a new approach to managing survey data in service of the Fragile Families Challenge, which they call “treating metadata as data.” Although the approach they present is a good first step, a more ambitious proposal could improve survey data analysis even more substantially. The author recommends that data collection efforts distribute an open-source set of tools for working with a particular data set the author calls data-specific functions. The goal of these functions is to codify best practices for working with the data in a set of functions for commonly used statistical software. These functions would be jointly developed by the users and distributers of the data. Building such functions would both shorten the learning curve for new users and improve the quality of the data, by making tacit knowledge about problems with the data explicit and easy to act on. © SAGE Publications Inc.. All rights reserved.

In supervised machine learning for author name disambiguation, negative training data are often dominantly larger than positive training data. This paper examines how the ratios of negative to positive training data can affect the performance of machine learning algorithms to disambiguate author names in bibliographic records. On multiple labeled datasets, three classifiers-Logistic Regression, Naive Bayes, and Random Forest-are trained through representative features such as coauthor names, and title words extracted from the same training data but with various positive-to-negative training data ratios. Results show that increasing negative training data can improve disambiguation performance but with a few percent of performance gains and sometimes degrade it. Logistic and Naive Bayes learn optimal disambiguation models even with a base ratio (1:1) of positive and negative training data. Also, the performance improvement by Random Forest tends to quickly saturate roughly after 1:10 similar to 1:15. These findings imply that contrary to the common practice using all training data, name disambiguation algorithms can be trained using part of negative training data without degrading much disambiguation performance while increasing computational efficiency. This study calls for more attention from author name disambiguation scholars to methods for machine learning from imbalanced data.

Author name ambiguity in a digital library may affect the findings of research that mines authorship data of the library. This study evaluates author name disambiguation in DBLP, a widely used but insufficiently evaluated digital library for its disambiguation performance. In doing so, this study takes a triangulation approach that author name disambiguation for a digital library can be better evaluated when its performance is assessed on multiple labeled datasets with comparison to baselines. Tested on three types of labeled data containing 5000 to 6 M disambiguated names, DBLP is shown to assign author names quite accurately to distinct authors, resulting in pairwise precision, recall, and F1 measures around 0.90 or above overall. DBLP's author name disambiguation performs well even on large ambiguous name blocks but deficiently on distinguishing authors with the same names. Compared to other disambiguation algorithms, DBLP's disambiguation performance is quite competitive, possibly due to its hybrid disambiguation approach combining algorithmic disambiguation and manual error correction. A discussion follows on strengths and weaknesses of labeled datasets used in this study for future efforts to evaluate author name disambiguation on a digital library scale.

Countries, research institutions, and scholars are interested in identifying and promoting high-impact and transformative scientific research. This paper presents a novel set of text-and citation-based metrics that can be used to identify high-impact and transformative works. The 11 metrics can be grouped into seven types: Radical-Generative, Radical-Destructive, Risky, Multidisciplinary, Wide Impact, Growing Impact, and Impact (overall). The metrics are exemplified, validated, and compared using a set of 10,778,696 MEDLINE articles matched to the Science Citation Index Expanded (TM). Articles are grouped into six 5-year periods (spanning 1983-2012) using publication year and into 6,159 fields constructed using comparable MeSH terms, with which each article is tagged. The analysis is conducted at the level of a field-period pair, of which 15,051 have articles and are used in this study. A factor analysis shows that transformativeness and impact are positively related (rho = .402), but represent distinct phenomena. Looking at the subcomponents of transformativeness, there is no evidence that transformative work is adopted slowly or that the generation of important new concepts coincides with the obsolescence of existing concepts. We also find that the generation of important new concepts and highly cited work is more risky. Finally, supporting the validity of our metrics, we show that work that draws on a wider range of research fields is used more widely.