Valid auto-models for spatially autocorrelated occupancy and abundance data
Valid auto-models for spatially autocorrelated occupancy and abundance data
复制标题
DOI：
10.1111/2041-210x.12402
复制
发表时间：
2015-10-01
影响因子：
6.6
通讯作者：
Wintle, Brendan A.
中科院分区：
文献类型：
--
作者：
Bardos, David C.;Guillera-Arroita, Gurutzeta;Wintle, Brendan A.
在广义线性模型中，空间自相关的物种丰度或分布数据集通常产生空间自相关残差；因此，需要一个更广泛的建模框架。自逻辑和相关的自模型，实现近似自协变量回归，提供简单和直接的空间人口过程建模。自Augustin， Mugglestone和Buckland （Journal of applied ecology, 1996,33, 339）使用混合估计方法分析马鹿普查数据以来，自逻辑模型在生态学中得到了广泛应用。该方法将最大伪似然估计与缺失数据的Gibbs抽样相结合。然而，Dormann（生态建模，2007,207,234）质疑自逻辑回归的有效性，甚至对完全观察到的数据，给出了在模拟鼻虫数据分析中明显低估协变量参数的例子。Dormann等等。（Ecography, 2007, 30,609）将这一批评扩展到auto-Poisson和某些auto-normal模型，再次发现协变量参数的自协变量回归估计与用于生成snouter数据的值几乎没有相似之处。我们注意到，上述所有研究都采用了与自模型定义不一致的邻域加权方案；在auto-Poisson案例中，进一步的不一致是未能排除合作互动。我们使用经验和模拟数据集研究这些实现错误对自动模型估计的影响。我们表明，当使用有效权重重新分析snouter数据时，协变量参数得到了非常不同的估计。对于自逻辑模型和自正态模型，新的估计与用于生成snouter模拟的值非常吻合。对马鹿数据的重新分析表明，无效的邻域加权只会对整个数据集产生很小的估计误差，但对地理子样本会产生较大的误差。大量采用自逻辑回归的论文使用这些无效邻域权重，这些无效邻域权重作为默认选项嵌入在广泛使用的spdeep '空间依赖软件包中。使用无效邻域权重进行的自逻辑分析将在很大程度上是错误的，可能会有很大差异。这些分析可以很容易地通过使用spdep'中可用的有效邻域加权来纠正。缺失数据的混合估计方法很容易适用于有效的邻域加权方案，并且在R中实现了用于稀疏存在-缺失数据的应用。
Spatially autocorrelated species abundance or distribution data sets typically generate spatially autocorrelated residuals in generalized linear models; a broader modelling framework is therefore required. Auto-logistic and related auto-models, implemented approximately as autocovariate regression, provide simple and direct modelling of spatial population processes. The auto-logistic model has been widely applied in ecology since Augustin, Mugglestone and Buckland (Journal of Applied Ecology, 1996, 33, 339) analysed red deer census data using a hybrid estimation approach, combining maximum pseudo-likelihood estimation with Gibbs sampling of missing data. However, Dormann (Ecological Modelling, 2007, 207, 234) questioned the validity of auto-logistic regression even for fully observed data, giving examples of apparent underestimation of covariate parameters in analysis of simulated snouter' data. Dormann etal. (Ecography, 2007, 30, 609) extended this critique to auto-Poisson and certain auto-normal models, finding again that autocovariate-regression estimates for covariate parameters bore little resemblance to values employed to generate snouter' data. We note that all the above studies employ neighbourhood weighting schemes inconsistent with auto-model definitions; in the auto-Poisson case, a further inconsistency was the failure to exclude cooperative interactions. We investigate the impact of these implementation errors on auto-model estimation using both empirical and simulated data sets. We show that when snouter' data are reanalysed using valid weightings, very different estimates are obtained for covariate parameters. For auto-logistic and auto-normal models, the new estimates agree closely with values used to generate the snouter' simulations. Re-analysis of the red deer data shows that invalid neighbourhood weightings generate only small estimation errors for the full data set, but larger errors occur on geographic subsamples. A substantial fraction of papers employing auto-logistic regression use these invalid neighbourhood weightings, which were embedded as default options in the widely used spdep' spatial dependence package for R. Auto-logistic analyses conducted using invalid neighbourhood weightings will be erroneous to an extent that can vary widely. These analyses can easily be corrected by using valid neighbourhood weightings available in spdep'. The hybrid estimation approach for missing data is readily adapted for valid neighbourhood weighting schemes and is implemented here in R for application to sparse presence-absence data.