Over the last four decades, the average Gaussian-risk-adjusted return on a stock portfolio that goes long in the largest banks and short in the smallest banks is minus 7 %. Moreover, this portfolio provides US investors with insurance against recessions, even though the cash flows of large banks seem more exposed to macroeconomic risk. Using the rare events model of ?, we interpret the 7% as a ...

In rea l -wor ld domains a concept to be learned may be unwieldy and the environment may be less than ideal. One combinat ion of difficulties occurs if the concept is probabi l ist ic and the learning si tuat ion is dynamic. In this case, the data may be noisy and biased. These difficulties arise when learning evaluation functions, which can be considered as concepts. A representative problem, ...

It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention. Here we investigate how unexpected these extreme events are. We propose a method that, given some information on the items, quantifies the predictability of events, i.e., the potential of identifying in advance the most successful it...

Extreme events, by definition, cause much harm to people, property, and the natural world. Such events can result from the vagaries of nature (floods or earthquakes) or from technological failure or unintentional human error (Chernobyl or Bhopal). More recently we have witnessed another form of extreme hazard, resulting from terrorism. This paper examines the complex interplay between emotion a...

The more tests we perform on a set of data, the more likely we are to reject the null hypothesis when it is true (i.e., a “Type I” error). This is a consequence of the logic of hypothesis testing: We reject the null hypothesis if we witness a rare event. But the larger the number of tests, the easier it is to find rare events and therefore the easier it is to make the mistake of thinking that t...

Abstract This paper shows that one cannot learn the probability of rare events without imposing further structural assumptions. The event of interest is that of obtaining an outcome outside the coverage of an i.i.d. sample from a discrete distribution. The probability of this event is referred to as the “missing mass”. The impossibility result can then be stated as: the missing mass is not dist...

In response to an extreme event, individuals on social media demonstrate interesting behaviors in information seeking and sharing, depending on their backgrounds. Existing studies have attempted to analyze and understand the regularities of human responses during an extreme event, e.g., their spatiotemporal patterns. However, most of them focus on the general patterns of human collective online...

E very year, the Bulletin of the AMS publishes an annual report on the State of the Climate [e.g., see the Blunden and Arndt (2012) supplement to this issue]. That report does an excellent job of documenting global weather and climate conditions of the previous year and putting them into accurate historical perspective. But it does not address the causes. One of the reasons is that the scientis...

Considering a disastrous earthquake as a rare event, the aim of this study is to apply the proposed data construction method (DCM) to determine the possible distribution pattern of disastrous earthquakes in Taiwan. Owing to the availability of only a limited amount of data and based on the multiset division of DCM, virtual samples have been generated. The procedure is illustrated by a numerical...

BACKGROUND This study explored the role of meaning in the link between stress and disordered eating, in particular focusing on social rank. METHOD Two hundred and eleven women completed measures of eating pathology, depression, social comparison and life events where life events were assessed in terms of general loss, threat, shame and loss of social status. RESULTS Events involving loss of...