当前位置: X-MOL 学术Environmetrics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
On the effect of preferential sampling in spatial prediction
Environmetrics ( IF 1.7 ) Pub Date : 2012-10-11 , DOI: 10.1002/env.2169
Alan E Gelfand 1 , Sujit K Sahu , David M Holland
Affiliation  

The choice of the sampling locations in a spatial network is often guided by practical demands. In particular, many locations are preferentially chosen to capture high values of a response, for example, air pollution levels in environmental monitoring. Then, model estimation and prediction of the exposure surface become biased due to the selective sampling. Since prediction is often the main utility of the modeling, we suggest that the effect of preferential sampling lies more importantly in the resulting predictive surface than in parameter estimation. Our contribution is to offer a direct simulation-based approach to assessing the effects of preferential sampling. We compare two predictive surfaces over the study region, one originating from the notion of an 'operating' intensity driving the selection of monitoring sites, the other under complete spatial randomness. We can consider a range of response models. They may reflect the operating intensity, introduce alternative informative covariates, or just propose a flexible spatial model. Then, we can generate data under the given model. Upon fitting the model and interpolating (kriging), we will obtain two predictive surfaces to compare. It is important to note that we need suitable metrics to compare the surfaces and that the predictive surfaces are random, so we need to make expected comparisons.

中文翻译:

优先采样在空间预测中的作用

空间网络中采样位置的选择通常以实际需求为指导。特别是,优先选择许多位置来捕获响应的高值,例如环境监测中的空气污染水平。然后,由于选择性采样,暴露表面的模型估计和预测变得有偏差。由于预测通常是建模的主要用途,因此我们建议优先采样的影响更重要的是产生的预测表面而不是参数估计。我们的贡献是提供一种直接基于模拟的方法来评估优先抽样的影响。我们比较了研究区域的两个预测表面,一个源自驱动监测站点选择的“操作”强度概念,另一个在完全空间随机性下。我们可以考虑一系列响应模型。它们可能反映操作强度,引入替代信息协变量,或者只是提出一个灵活的空间模型。然后,我们可以在给定的模型下生成数据。在拟合模型并进行插值(克里金法)后,我们将获得两个预测曲面进行比较。需要注意的是,我们需要合适的指标来比较曲面,并且预测曲面是随机的,因此我们需要进行预期的比较。我们将获得两个预测曲面进行比较。需要注意的是,我们需要合适的指标来比较曲面,并且预测曲面是随机的,因此我们需要进行预期的比较。我们将获得两个预测曲面进行比较。需要注意的是,我们需要合适的指标来比较曲面,并且预测曲面是随机的,因此我们需要进行预期的比较。
更新日期:2012-10-11
down
wechat
bug