Avoiding the misuse of BLUP in behavioural ecology.
Avoiding the misuse of BLUP in behavioural ecology.
复制标题
DOI：
10.1093/beheco/arx023
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Wilson AJ
中科院分区：
文献类型：
--
作者：
Houslay TM;Wilson AJ
对动物人格的原因和后果的研究有望带来令人兴奋的见解，但广泛使用的测试可能会导致虚假的结果：当在二次分析中使用个体水平随机效应的预测时，它们的误差不会结转，导致“假阳性”错误的可能性增加。我们展示了替代方法如何使行为生态学家测试的原因和后果的个人行为变化的假设，同时占随机效应中固有的不确定性。在认识到群体水平上不稳定性状的“黄金均值”周围的变化包含有生物学意义的信息后，行为生态学家越来越多地关注探索个体行为变化的原因和后果。这些都是令人兴奋的新方向的领域，在不小的一部分通过采用混合效应建模技术，使分区之间和内部的个人行为变化的帮助。从这些模型中提取个体随机效应的预测用于后续分析（例如，人格特质与其他个体特质之间的预测，如认知，生理或健康相关的测量）已经变得司空见惯。然而，这些预测是由大量的错误，没有结转，使进一步的测试容易受到虚假的P值从这些个人水平的点估计。我们简要总结了行为生态学家经常使用的统计方法的问题，并强调了混合模型框架内存在的强大的解决方案，提供教程，以帮助其实施。
Research of causes and consequences of animal personality promises exciting insights, yet widely used tests can lead to spurious results: when predictions of individual-level random effects are used in secondary analyses, their error is not carried forward, leading to increased likelihood of ‘false positive’ errors. We demonstrate how alternative approaches enable behavioural ecologists to test hypotheses about the causes and consequences of individual behavioural variation while accounting for the uncertainty inherent in the random effects. Having recognized that variation around the population-level “Golden Mean” of labile traits contains biologically meaningful information, behavioural ecologists have focused increasingly on exploring the causes and consequences of individual variation in behaviour. These are exciting new directions for the field, assisted in no small part by the adoption of mixed-effects modelling techniques that enable the partitioning of among- and within-individual behavioural variation. It has become commonplace to extract predictions of individual random effects from such models for use in subsequent analyses (for example, between a personality trait and other individual traits such as cognition, physiology, or fitness-related measures). However, these predictions are made with large amounts of error that is not carried forward, rendering further tests susceptible to spurious P values from these individual-level point estimates. We briefly summarize the problems with such statistical methods that are used regularly by behavioural ecologists, and highlight the robust solutions that exist within the mixed model framework, providing tutorials to aid in their implementation.
登录
查看更多内容
影响因子：
2.2
作者：
Carere, Claudio;Caramaschi, Doretta;Fawcett, Tim W.
通讯作者：
Fawcett, Tim W.
影响因子：
2.5
作者：
Betini, Gustavo S.;Norris, D. Ryan
通讯作者：
Norris, D. Ryan
影响因子：
2.5
作者：
Brent, Lauren J. N.;Semple, Stuart;Platt, Michael L.
通讯作者：
Platt, Michael L.
影响因子：
8.8
作者：
Arroyo, Beatriz;Mougeot, Francois;Bretagnolle, Vincent
通讯作者：
Bretagnolle, Vincent
影响因子：
2.5
作者：
Dammhahn, Melanie;Almeling, Laura
通讯作者：
Almeling, Laura