在fMRI分析中寻求对线性解决方案的无意偏见
Jeanette A Mumford1, Michael I Demidenko1, James M Bjork2
1Department of Psychology, Stanford University.
bioRxiv : the preprint server for biology
|July 16, 2025
概括
任务功能磁共振成像 (fMRI) 的对线性可能会导致结果偏差. 一个新的基于对比的差异膨胀因子 (cVIF) 量化了对线性影响,引导研究人员在fMRI分析中进行公正的参数估计.
科学领域:
- 神经成像是一种神经成像.
- 认知神经科学 认知神经科学
- 统计建模 统计建模
背景情况:
- 任务功能磁共振成像 (fMRI) 时间序列模型中的对线性可以减少统计功率.
- 以减少对线性为目的的后期模型修改可能会在参数估计中引入偏差.
- 这些问题在任务fMRI研究中很普遍,包括那些使用货币激励延迟 (MID) 任务的研究.
研究的目的:
- 引入一种新的方法,即基于对比的差异膨胀系数 (cVIF),用于量化对线性对任务fMRI测量的影响.
- 评估任务fMRI中常见的对线性减少策略的偏差影响.
- 提出一个"和"模型作为一种策略,以减轻偏差,同时管理对线性.
主要方法:
- 开发和应用基于对比的差异膨胀系数 (cVIF) 来评估对线性.
- 从青少年大脑认知发展 (ABCD) 研究中分析货币激励延迟 (MID) 任务数据.
- 来自"和"模型的参数估计与采用对线性减少技术的模型的参数估计的比较.
主要成果:
- cVIF提供了一个直接测量对线性对任务相关对比的影响.
- 诸如回归器遗漏,冲动响应函数和忽视响应时间变化等策略可以显著偏差对比估计.
- 拟议的"和"模型,包括包括响应时间在内的所有任务组件,在保持可接受的对线性水平的同时,证明了减少偏差.
结论:
- 任务fMRI中的对线性需要仔细考虑,因为常见的缓解策略可以引入偏差.
- cVIF是评估对线性对fMRI结果的影响的一个有价值的工具.
- "和"模型方法为在任务fMRI分析中获得较少偏差的参数估计提供了一个有希望的方法.
相关概念视频
Bias
5.0K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
5.0K
Bias in Epidemiological Studies
695
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
695


