BACKGROUND Departures from power law group size frequency distributions have been proposed as a useful tool to link individual behavior with population patterns and dynamics, although examples are scarce for wild animal populations. METHODOLOGY/PRINCIPAL FINDINGS We studied a population of Lesser kestrels (Falco naumanni) breeding in groups (colonies) from one to ca. 40 breeding pairs in 10,0...

Power-law frequency distributions characterize a wide array of natural phenomena. In ecology, biology, and many physical and social sciences, the exponents of these power laws are estimated to draw inference about the processes underlying the phenomenon, to test theoretical models, and to scale up from local observations to global patterns. Therefore, it is essential that these exponents be est...

We analyze time evolution of statistical distributions of citations to scientific papers published in the same year. While these distributions seem to follow the power-law dependence we find that they are nonstationary and the exponent of the power-law fit decreases with time and does not come to saturation. We attribute the nonstationarity of citation distributions to different longevity of th...

a Ohio University, College of Business, Athens, OH 45701, United States b Indiana University, Kelley School of Business, Bloomington, IN 47405, United States c University of Massachusetts-Boston, College of Management, Boston, MA 02125, United States d Queensland University of Technology, Business School, Brisbane Qld 4001, Australia e Jönköping International Business School, Sweden f Kedge Bus...

The expansion of ionization fronts in uniform and spherically symmetric power-law density distributions is a well-studied topic. However, in many situations, such as a star formed at the edge of a molecular cloud core, an offset power-law density distribution would be more appropriate. In this paper a few of the main issues of the formation and expansion of HII regions in such media are outline...

In this talk I will propose that prior distributions can be powerful ways to put computational linguistics knowledge into your models, and give two examples from my own work. Firstly, hierarchical priors can allow you to specify relationships among different components of your model so that the information learned in one component can be shared with the rest, improving the estimation of paramet...