In research fields like informetrics or patent research, international comparisons are part of their core business. One class of measures used in such comparisons consists of affinity indices. Here, relations of shares are calculated to express the relation between two actors X and Y. Even though this group of affinity indices already has many members, we think that based on pure logic, they still miss the point. For this reason, we introduce the RIC index. This index compares two shares: the share of actor Y within a given set X to the share of Y within the complement of X. After motivating and introducing this new index, we show some of its basic characteristics, the most interesting one being that increased collaboration between two countries leads to an increase in the value of RIC. Moreover, this index is asymmetric. The RIC index is illustrated with the examples of China and the USA within the global network of collaboration 2000-2020.

The Activity Index (AI) is a well-known index for comparing the contribution of different entities on various fields, for example scientific articles with authorships from different countries structured into various subjects as arts, engineering, economics and so on. This index lacks important properties; the most demonstrative one is its characteristic to be lower but not upper bounded. Further, we will show that the AI is a log-normal distribution and that it is common in literature to transform the AI by the logarithm to a normal distribution. Last, we will present an alternative transformation special for longitudinal data, that transforms the AI to a normal distribution, too, without the negative properties of the logarithm like the loss of data if the logarithm is applied. This newly introduced index called Normalized AI (NAI) will be calculated by expansion the relation of the AI in dividend as in divisor. It will not converge to the logarithm of the AI, but to the logarithm of the AI if z-standardized by each entity-field combination.

This paper examines the distribution of Nobel laureates in Physiology/Medicine, Physics, and Chemistry across countries and research organizations. We provide basic information about where future laureates received their education and/or conducted their research, then present heat maps depicting country and organizational specialization patterns. In addition, we identify the organizational ultra-elite in science: universities and research institutes that show continuously above-average numbers of future laureates, typically in one career phase. Furthermore, we identify those universities and research institutes that have undergone considerable growth (or decline) in their capabilities for highly innovative research. Also, we compare country-specific profiles with those at the organizational level. Our findings are interpreted in the light of findings from comparative-historical studies.

The Activity Index (AI) is a well-known index for comparing the contribution of different entities on various fields, for example scientific articles from different countries on various subjects, but it lacks important properties. We will show, that the AI is a log-normal distribution and that it is common in literature to transform the AI by the logarithm to a normal distribution. Last, we will present an alternative transformation special for longitudinal data, that transforms the AI to a normal distribution, too, without the negative properties of the logarithm.

Purpose We aim to extend our investigations related to the Relative Intensity of Collaboration (RIC) indicator, by constructing a confidence interval for the obtained values. Design/methodology/approach We use Mantel-Haenszel statistics as applied recently by Smolinsky, Klingenberg, and Marx. Findings We obtain confidence intervals for the RIC indicator Research limitations It is not obvious that data obtained from the Web of Science (or any other database) can be considered a random sample. Practical implications We explain how to calculate confidence intervals. Bibliometric indicators are more often than not presented as precise values instead of an approximation depending on the database and the time of measurement. Our approach presents a suggestion to solve this problem. Originality/value Our approach combines the statistics of binary categorical data and bibliometric studies of collaboration.