Damage models for natural hazards are used for decision making on reducing and transferring risk. The damage estimates from these models depend on many variables and their complex sometimes nonlinear relationships with the damage. In recent years, data‐driven modeling techniques have been used to capture those relationships. The available data to build such models are often limited. Therefore, in practice it is usually necessary to transfer models to a different context. In this article, we show that this implies the samples used to build the model are often not fully representative for the situation where they need to be applied on, which leads to a “sample selection bias.” In this article, we enhance data‐driven damage models by applying methods, not previously applied to damage modeling, to correct for this bias before the machine learning (ML) models are trained. We demonstrate this with case studies on flooding in Europe, and typhoon wind damage in the Philippines. Two sample selection bias correction methods from the ML literature are applied and one of these methods is also adjusted to our problem. These three methods are combined with stochastic generation of synthetic damage data. We demonstrate that for both case studies, the sample selection bias correction techniques reduce model errors, especially for the mean bias error this reduction can be larger than 30%. The novel combination with stochastic data generation seems to enhance these techniques. This shows that sample selection bias correction methods are beneficial for damage model transfer. 相似文献
VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - To encourage methodological pluralism in the field, this paper examines an illustrative sample of articles that apply... 相似文献
Clinical Social Work Journal - System enactments are co-created phenomena characterized by confounding and emotionally charged multi-person interactions that emerge through the convergence of... 相似文献
This paper shows that mobile money technology—an electronic wallet service that allows users to deposit, transfer, and receive money using their mobile phones—is positively correlated with increased school participation of children in school age. By using data from 4 African countries, we argue that, by reducing transaction costs, and by making it easier and less expensive to receive remittances, mobile money reduces the need for coping strategies that are detrimental to child development, such as withdrawing children from school and sending them to work. We find that mobile money increases the chances of children attending school. This finding is robust to different empirical models. In a nutshell, our results show that 1 million children could start attending school in low-income countries if mobile money was available to all.
Environmental scanning is a broadly defined concept, having first received attention from scholars in the late 1960s. Over the years a number of similar and overlapping constructs have emerged in management literature. The aim of this study, via a systematic review and thematic analysis of relevant empirical research, is to consolidate foundation environmental scanning knowledge, demonstrate how scanning research has developed and fragmented over time, and propose an agenda for future research. The first contribution of our review is a new typology of environmental scanning research made up of five discrete research views, which provides a more comprehensive and contemporary overview of the field than previous studies. The second is a proposed agenda for future research that explicitly acknowledges the role of technology, an area that is presently underdeveloped in foundation scanning literature. The third contribution is to signpost future directions for research on scanning and organisational performance using a number of theoretical perspectives. The overall outcome of our review is to move scanning research on from increasingly incremental contributions concerned with context to a place where the changing role of technology and the mechanisms through which environmental scanning contributes to competitive advantage can be more thoroughly understood. 相似文献