Mumford Jeanette A, Demidenko Michael I, Bjork James M, Chaarani Bader, Feczko Eric J, Garavan Hugh P, Hagler Donald J, Nelson Steven M, Wager Tor D, Poldrack Russell A
Department of Psychology, Stanford University.
Institute for Drug and Alcohol Studies, Virginia Commonwealth University.
bioRxiv. 2025 Jun 18:2025.01.14.633053. doi: 10.1101/2025.01.14.633053.
In task functional magnetic resonance imaging (fMRI), collinearity between task regressors in time series models may impact power. When collinearity is identified after data collection, researchers often modify the model in an effort to reduce collinearity. However, some model adjustments are suboptimal and may introduce bias into parameter estimates. Although relevant to many task-fMRI studies, we highlight these issues using the Monetary Incentive Delay (MID) task data from the Adolescent Brain Cognitive Development (ABCD) study. We introduce a procedure to more directly quantify the impact of collinearity on task-relevant measures: a contrast-based variance inflation factor (cVIF). We also show that collinearity reduction strategies-such as omitting regressors for specific task components, using impulse regressors for extended activations, and ignoring response time variability-can bias contrast estimates. Finally, we present a "Saturated" model that includes all task components, including response times, aiming to reduce these biases while maintaining comparable levels of collinearity, as assessed by cVIF.
在任务功能磁共振成像（fMRI）中，时间序列模型中任务回归变量之间的共线性可能会影响功效。在数据收集后识别出共线性时，研究人员通常会修改模型以努力降低共线性。然而，一些模型调整并不理想，可能会在参数估计中引入偏差。尽管这些问题与许多任务fMRI研究相关，但我们使用青少年大脑认知发展（ABCD）研究中的货币激励延迟（MID）任务数据来突出这些问题。我们引入了一种程序，以更直接地量化共线性对与任务相关指标的影响：基于对比的方差膨胀因子（cVIF）。我们还表明，共线性降低策略，如省略特定任务组件的回归变量、对延长激活使用脉冲回归变量以及忽略反应时间变异性，可能会使对比估计产生偏差。最后，我们提出了一个“饱和”模型，该模型包括所有任务组件，包括反应时间，旨在减少这些偏差，同时保持由cVIF评估的相当水平的共线性。
