Model Selection in Occupancy Models: Inference versus Prediction-猫眼课题宝

DOI：

10.1101/2022.03.01.482466

发表时间：

2022-03

期刊：

bioRxiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Peter S. Stewart;P. Stephens;R. A. Hill;M. Whittingham;W. Dawson

占有率模型是应用生态学家研究物种发生的模式和驱动因素的重要工具，但它们的使用需要一种方法来选择具有不同占有率和检测协变量的模型。信息论方法采用了信息标准，如Akaike的信息标准(AIC)，可以说是生态学中最流行的模型选择方法，经常用于选择占用模型。然而，由于一种被称为对撞机偏差的现象，信息论方法可能会选择产生不准确参数估计的模型。通过仿真，我们研究了碰撞偏差(使用一个称为M-偏差的说明性例子)在占用模型和检测过程中的后果，并探索了使用AIC和一种常见的替代方案Schwarz准则(或贝叶斯信息准则，BIC)对模型选择的影响。我们发现，当M偏差存在于占用过程中时，AIC和BIC选择了不准确估计焦点占用协变量影响的模型，同时产生了对站点级别占用概率的更准确的预测。相比之下，检测过程中的M偏倚不影响焦点估计；所有模型都做出了准确的推断，而AIC/BIC-BEST模型的站点水平预测略准确一些。我们的结果表明，如果模型的唯一目的是预测，则可以使用信息标准来选择入住率协变量，但如果目的是了解环境变量如何影响入住率，则必须更加谨慎地对待。相比之下，检测协变量通常可以使用信息标准来选择，而不考虑模型的目的。这些发现说明了在生态模型中区分参数推断和预测任务的重要性。此外，我们的结果强调了在观察性研究中使用信息标准来比较不同的生物学假说的问题。完整复制我们的模拟和分析的开放研究声明代码可在以下网址获得：https://zenodo.org/badge/latestdoi/462801230

Occupancy models are a vital tool for applied ecologists studying the patterns and drivers of species occurrence, but their use requires a method for selecting between models with different sets of occupancy and detection covariates. The information-theoretic approach, which employs information criteria such as Akaike’s Information Criterion (AIC) is arguably the most popular approach for model selection in ecology and is often used for selecting occupancy models. However, the information-theoretic approach risks selecting models which produce inaccurate parameter estimates, due to a phenomenon called collider bias. Using simulations, we investigated the consequences of collider bias (using an illustrative example called M-bias) in the occupancy and detection processes of an occupancy model, and explored the implications for model selection using AIC and a common alternative, the Schwarz Criterion (or Bayesian Information Criterion, BIC). We found that when M-bias was present in the occupancy process, AIC and BIC selected models which inaccurately estimated the effect of the focal occupancy covariate, while simultaneously producing more accurate predictions of the site-level occupancy probability. In contrast, M-bias in the detection process did not impact the focal estimate; all models made accurate inferences, while the site-level predictions of the AIC/BIC-best model were slightly more accurate. Our results demonstrate that information criteria can be used to select occupancy covariates if the sole purpose of the model is prediction, but must be treated with more caution if the purpose is to understand how environmental variables affect occupancy. By contrast, detection covariates can usually be selected using information criteria regardless of the model’s purpose. These findings illustrate the importance of distinguishing between the tasks of parameter inference and prediction in ecological modelling. Furthermore, our results underline concerns about the use of information criteria to compare different biological hypotheses in observational studies. Open Research Statement Code to fully reproduce our simulations and analyses is available at: https://zenodo.org/badge/latestdoi/462801230

Model Selection in Occupancy Models: Inference versus Prediction

文献摘要

相似文献