Scientometric analysis of geostatistics using multivariate methods

Abstract

Multivariate methods were successfully employed in a comprehensive scientometric analysis of geostatistics research, and the publications data for this research came from the Science Citation Index and spanned the period from 1967 to 2005. Hierarchical cluster analysis (CA) was used in publication patterns based on different types of variables. A backward discriminant analysis (DA) with appropriate statistical tests was then conducted to confirm CA results and evaluate the variations of various patterns. For authorship pattern, the 50 most productive authors were classified by CA into 4 groups representing different levels, and DA produced 92.0% correct assignment with high reliability. The discriminant parameters were mean impact factor (MIF), annual citations per publication (ACPP), and the number of publications by the first author; for country/region pattern, CA divided the top 50 most productive countries/regions into 4 groups with 95.9% correct assignments, and the discriminant parameters were MIF, ACCP, and independent publication (IP); for institute pattern, 3 groups were identified from the top 50 most productive institutes with nearly 88.0% correct assignment, and the discriminant parameters were MIF, ACCP, IP, and international collaborative publication; last, for journal pattern, the top 50 most productive journals were classified into 3 groups with nearly 98.0% correct assignment, and its discriminant parameters were total citations, impact factor and ACCP. Moreover, we also analyzed general patterns for publication document type, language, subject category, and publication growth. F. ZHOU et al.: Multivariate analysis of geostatistics 266 Scientometrics 73 (2007)

Multivariate approach to classify research institutes according to their outputs: The case of the CSIC's institutes

“…Other studies have used partial approaches based mainly on bibliometric data in order to classify journals (Schubert and Braun, 1996), articles in thematic categories (Glänzel and Schubert, 2003), authors by their publications and citations (Zhou et al, 2007;Harris and Kaine, 1994), article-related indicators according to the features they measure (Bollen et al, 2009), research institutes by their publications (Chen and Liu, 2006;Thijs and Glänzel, 2008) and to build thematic maps from bibliographic data (Polanco et al, 1998).…”

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

“…Discriminant function analysis is a method of analyzing dependence that is a special case of canonical correlation used to discriminate between two or more groups on the basis of discriminant parameters [44]. The DFA shares all the usual assumptions of correlation, requiring linear and homoscedastic relationships, and untruncated interval or near interval data.…”

Characteristics of research in China assessed with Essential Science Indicators

“…The indicator, average citations per publication is more useful than the total citations for uncovering peak citation trends (Zhou et al 2007). Impact factor has the advantage of already being in existence and is a good indicator for scientific evaluation (Hoeffel 1998).…”