Does research with statistics have more impact? The citation rank advantage of structural equation modeling

Abstract

Statistics are essential to many areas of research and individual statistical techniques may change the ways in which problems are addressed as well as the types of problems that can be tackled. Hence, specific techniques may tend to generate high‐impact findings within science. This article estimates the citation advantage of a technique by calculating the average citation rank of articles using it in the issue of the journal in which they were published. Applied to structural equation modeling (SEM) and four related techniques in 3 broad fields, the results show citation advantages that vary by technique and broad field. For example, SEM seems to be more influential in all broad fields than the 4 simpler methods, with one exception, and hence seems to be particularly worth adding to statistical curricula. In contrast, Pearson correlation apparently has the highest average impact in medicine but the least in psychology. In conclusion, the results suggest that the importance of a statistical technique may vary by discipline and that even simple techniques can help to generate high‐impact research in some contexts.

Mendeley readership counts: An investigation of temporal and disciplinary differences

“…The social reference sharing website Mendeley is designed to help users to manage and share their academic references (Henning & Reichelt, ). As a side effect, it is possible to count readers to generate indicators for academic articles (Li et al., ), whole journals (Haustein & Siebenlist, ), or for knowledge transfer between disciplines (Mohammadi & Thelwall, ) and countries (Thelwall & Maflahi, in press), or for triangulation with citations in bibliometric studies (Sud & Thelwall, in press; Thelwall & Wilson, in press). Most people registering academic articles in Mendeley have already read them or intend to read them (Mohammadi, Thelwall, & Kousha, in press) and so it seems reasonable to use the term reader count to refer to the number of Mendeley users registering an article in their personal libraries.…”

Understanding the travel decision-making processes of COVID-19-vaccinated South Korean travelers

“…The most representative analytical technique to analyze non-experimental causality in the field of social science is Structural Equation Modeling, introduced by Keesling [ 47 ] and Wiley [ 48 ] as a combination of path analysis and confirmatory factor analysis. The method has seen a remarkable increase in domestic and international use because of its various advantages [ 49 ].…”

Financial behavior among young adult consumers: the influence of self-determination and financial psychology

“…The most effective technique for analyzing causal relationships is probably structural equation modeling (SEM). This method is a combined form of path analysis and Figure 2 Methodological framework and hypothesis model confirmatory factor analysis and many consumer behavior researchers have used them (Thelwall and Wilson, 2016). The number of papers published using only correlation, regression and factor analysis decreases.…”

“…The number of papers published using only correlation, regression and factor analysis decreases. According to Thelwall and Wilson (2016), the late 1990s saw an astounding increase in the publication of social science articles on structural equation models, about 50 per year.…”