A solution to dependency: using multilevel analysis to accommodate nested data
A solution to dependency: using multilevel analysis to accommodate nested data
复制标题
DOI：
10.1038/nn.3648
复制
发表时间：
2014-04-01
影响因子：
25
通讯作者：
van der Sluis, Sophie
中科院分区：
文献类型：
--
作者：
Aarts, Emmeke;Verhage, Matthijs;van der Sluis, Sophie
在神经科学中，从单个研究对象（例如，来自一种动物的多个神经元）收集多个观察结果的实验设计很常见：来自五种知名期刊的314篇评论论文中有53%包含这种类型的数据。这些所谓的“嵌套设计”产生的数据不能被认为是独立的，因此违反了传统统计方法（如t检验）的独立性假设。忽略这种依赖性会导致错误地得出结论的概率，即效应具有统计学显著性，远高于（高达80%）标称a水平（通常设置为5%）。我们讨论了影响I型错误率和嵌套数据的统计功效的因素，以及在数据嵌套时确定最佳研究设计的方法。值得注意的是，实验设计的优化几乎总是涉及收集更多真正独立的观察结果，而不是来自一个研究对象的更多观察结果。
In neuroscience, experimental designs in which multiple observations are collected from a single research object (for example, multiple neurons from one animal) are common: 53% of 314 reviewed papers from five renowned journals included this type of data. These so-called 'nested designs' yield data that cannot be considered to be independent, and so violate the independency assumption of conventional statistical methods such as the t test. Ignoring this dependency results in a probability of incorrectly concluding that an effect is statistically significant that is far higher (up to 80%) than the nominal a level (usually set at 5%). We discuss the factors affecting the type I error rate and the statistical power in nested data, methods that accommodate dependency between observations and ways to determine the optimal study design when data are nested. Notably, optimization of experimental designs nearly always concerns collection of more truly independent observations, rather than more observations from one research object.