Model choice is a fundamental and much discussed activity in the analysis of datasets. Nonnested hierarchical models introducing random effects may not be handled by classical methods. Bayesian approaches using predictive distributions can be used though the formal solution, which includes Bayes factors as a special case, can be criticised. We propose a predictive criterion where the goal is go...

We present a hierarchical Bayesian model for learning efficient codes of higher-order structure in natural images. The model, a non-linear generalization of independent component analysis, replaces the standard assumption of independence for the joint distribution of coefficients with a distribution that is adapted to the variance structure of the coefficients of an efficient image basis. This ...

This paper presents a model of local network effects in which agents connected in a social network each value the adoption of a product by a heterogeneous subset of other agents in their neighborhood, and have incomplete information about the structure and strength of adoption complementarities between all other agents. I show that the symmetric Bayes-Nash equilibria of this network game are in...

In recent years, many areas of China have suffered from serious haze pollution, which greatly affects human health and daily life. It is of policy importance to understand the factors that influence the spatial concentration of PM2.5. Based on data from 74 cities with PM2.5 monitoring stations in 2013 and 2014, this study presents the overall haze situation in China and explores the determinant...

Cognitive tasks recruit multiple brain regions. Understanding how these regions influence each other (the network structure) is an important step to characterize the neural basis of cognitive processes. Often, limited evidence is available to restrict the range of hypotheses a priori, and techniques that sift efficiently through a large number of possible network structures are needed (network ...

Working papers are in draft form. This working paper is distributed for purposes of comment and discussion only. It may not be reproduced without permission of the copyright holder. Copies of working papers are available from the author. The organizational theory of the multinational firm holds that foreignness is a liability, and specifically that lack of embeddedness in host-country social ne...

Objective. To pilot test an artificial intelligence (AI) algorithm that selects peer change agents (PCA) to disseminate HIV testing messaging in a population of homeless youth. Methods. We recruited and assessed 62 youth at baseline, 1 month (n = 48), and 3 months (n = 38). A Facebook app collected preliminary social network data. Eleven PCAs selected by AI attended a 1-day training and 7 weekl...

Network effects are often “local” Communication technologies, business networks, online marketplaces... The structure of underlying social or business networks affects the adoption of network goods An agent’s “local” network directly affects their value from adoption... ...but so does the structure of the rest of the social network Local networks are connected One’s neighbors’ local networks af...

abstract background: the pressure of consumption spots in eater supply systems is one of the most important hydraulic parameters can be used in optimized management of water distribution networks. since the pressure has some different effects on various parameters of the network management including its hydraulic functions, reliability, stability and leakage, its control is of great importance ...