Search

Regional interventions to prevent the spread of hospital-acquired infections, vaccination campaigns, and information dissemination strategies are examples of treatment interventions applied to members of a network with the intent of effecting a network-wide change. In designing clinical trials or determining policy changes, it may not be cost effective or otherwise possible to treat all actors of a network. There is a notable lack of study designs and statistical frameworks with which to plan a network-wide intervention in this context and analyze the resulting data. This paper builds off of the network autocorrelation model in order to provide such a framework for a pre-post study design. We derive key quantitative measures of the network-wide treatment effect, exact formulas for power analyses of these measures, and extensions for the context in which the network is unknown. As the treatment assignation is part of the network-wide treatment, we provide methods for determining the assignation which optimizes the overall treatment effect over all members of the network subject to any arbitrary set of implementation costs and cost constraint. We implement these methods on Clostridioides difficile data for the state of California, where the hospitals are linked through patient sharing. [ABSTRACT FROM AUTHOR]

SUMMARY Two key issues distinguish probabilistic seismic risk analysis of a lifeline or portfolio of structures from that of a single structure. Regional analysis must consider the correlation among lifeline components or structures in the portfolio, and the larger scope makes it much more computationally demanding. In this paper, we systematically identify and compare alternative methods for regional hazard analysis that can be used as the first part of a computationally efficient regional probabilistic seismic risk analysis that properly considers spatial correlation. Specifically, each method results in a set of probabilistic ground motion maps with associated hazard-consistent annual occurrence probabilities that together represent the regional hazard. The methods are compared according to how replicable and computationally tractable they are and the extent to which the resulting maps are physically realistic, consistent with the regional hazard and regional spatial correlation, and few in number. On the basis of a conceptual comparison and an empirical comparison for Los Angeles, we recommend a combination of simulation and optimization approaches: (i) Monte Carlo simulation with importance sampling of the earthquake magnitudes to generate a set of probabilistic earthquake scenarios (defined by source and magnitude); (ii) the optimization-based probabilistic scenario method, a mixed-integer linear program, to reduce the size of that set; (iii) Monte Carlo simulation to generate a set of probabilistic ground motion maps, varying the number of maps sampled from each earthquake scenario so as to minimize the sampling variance; and (iv) the optimization-based probabilistic scenario again to reduce the set of probabilistic ground motion maps. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]