Scientometric evaluation of Sankhya - the Indian Journal of Statistics

This paper critically analyses 199 peer-reviewed articles published in Sankhya during 2003 to 2007. It examines authorship pattern, collaboration trend among authors, predominant areas of statistical research, and time lag in publications. Subsequent analysis focuses on prolific contributors, degree of collaboration, collaboration density, active sub-domains of statistics and time lag trend. Findings reveal the following: (a) the number of articles reduced from 24.6% to 14.0% that conforms to the growth trend of statistical publications in India; (b) single-authored paper counts only 30%, the rest in collaboration either by two-authors (47%) or three-to-five-authors (23%) and average authorship accounts for 1.96 per paper; (c) contributors of Sankhya worked in highly collaborative manner and the degree of collaboration (CC=0.698) is quite significant; and (d) most of the bilateral and multilateral collaborations has emanated from 12 institutions of 5 different countries. Ranked list of profilic authors has been carried out using fractional counting method. It is observed that author productivity is not in agreement with Lotka's law, but productivity distribution data partially fits the law when the value of alpha approximated to 2.77 and the number of papers does not exceed two. Broad subject clusters, such as statistics (153) and probability theory (38) constituted about 96% of the contributed articles. Nonparametric inference (18%), parametric inference (15%), design of experiments (10%) and multivariate analysis (8%) are found to be active areas of research in statistics. The study shows an average time lag of fifteen months to publish an article, and a declining trend of time lags following second-degree polynomial type has been observed in this scholarly journal.