Certain similarities between the types of data reported in retrospective citation analyses and lifetime/survival/reliability models are noted. Graphical techniques much used in reliability analyses are exploited to throw further light on observed citation age distributions and these are then compared and contrasted with previously reported studies. These simple techniques allow systematic departures of empirical data from assumed theoretical models to be highlighted and the models to be compared.
The stochastic model proposed recently by the author to describe the citation process in the presence of obsolescence is further
investigated to illustrate the nth-citation distribution and the distribution of the total number of citations. The particular case where the latent rate
has a gamma distribution is analysed in detail and is shown to be able to agree well with empirical data.
In recent issues of the ISSI Newsletter, Egghe [2006a] proposed the g-index and Kosmulski  the h(2)-index, both claimed to be improvements on the original h-index proposed by Hirsch . The aim of this paper is to investigate the inter-relationships between these measures and also their time dependence
using the stochastic publication/citation model proposed by Burrell [1992, 2007a]. We also make some tentative suggestions regarding the relative merits of these three proposed measures.
It is a well-known empirical fact that when informetric processes are observed over an extending period of time, the entire
shape of the distribution changes. In particular, it has been shown that concentration aspects change. In this paper the recently
introduced co-concentration coefficient (C-CC) is investigated via simple stochastic models of informetric processes to investigate
its time-dependence. It is shown that it is important to distinguish between situations where the zero-producers can be counted
and those where they cannot. A previously published data set is used to illustrate how the empirical C-CC develops in time
and the general features are compared with those derived from the theoretical model.
Hirsch’s h-index gives a single number that in some sense summarizes an author’s research output and its impact. Since an
individual author’s h-index will be time-dependent, we propose instead the h-rate which, according to theory, is (almost)
constant. We re-analyse a previously published data set (Liang, 2006) which, although not of the precise form to properly test our model, reveals that in many cases we do not have a constant
h-rate. On the other hand this then suggests ways in which deeper scientometric investigations could be carried out. This
work should be viewed as complementary to that of Liang (2006).