Group items tagged

In the chaos of 1960s Detroit, a fledgling police union laid the groundwork for a system that, to this day, constrains discipline for officers accused of misconduct.

The damage we are not attending to is the deeper nature of the crisis-the collapse of multiple coupled complex systems. Societies the world over are experiencing what might be called the first complexity crisis in history. We should not have been surprised that a random mutation of a virus in a far-off city in China could lead in just a few short months to the crash of financial markets worldwide, the end of football in Spain, a shortage of flour in the United Kingdom, the bankruptcy of Hertz and Niemann-Marcus in the United States, the collapse of travel, and to so much more.

team of researchers concludes that a game-theory approach may offer new insights into both the spread and disruption of viruses, such as SARS-CoV-2. Its work, described in the Journal of the Royal Society Interface, applies a "signaling game" to an analysis of cellular processes in illuminating molecular behavior.

The analysis of questionnaires often involves representing the high-dimensional responses in a low-dimensional space (e.g., PCA, MCA, or t-SNE). However questionnaire data often contains categorical variables and common statistical model assumptions rarely hold. Here we present a non-parametric approach based on Fisher Information which obtains a low-dimensional embedding of a statistical manifold (SM). The SM has deep connections with parametric statistical models and the theory of phase transitions in statistical physics. Firstly we simulate questionnaire responses based on a non-linear SM and validate our method compared to other methods. Secondly we apply our method to two empirical datasets containing largely categorical variables: an anthropological survey of rice farmers in Bali and a cohort study on health inequality in Amsterdam. Compare to previous analysis and known anthropological knowledge we conclude that our method best discriminates between different behaviours, paving the way to dimension reduction as effective as for continuous data.