Handling Multiplicity in Neuroimaging Through Bayesian Lenses with Multilevel Modeling

• Published in: Neuroinformatics (Totowa, N.J.) Vol. 17; no. 4; pp. 515 - 545
• Main Authors: Chen, Gang, Xiao, Yaqiong, Taylor, Paul A., Rajendra, Justin K., Riggins, Tracy, Geng, Fengji, Redcay, Elizabeth, Cox, Robert W.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2019; Springer Nature B.V
• Subjects: Bayes Theorem; Bayesian analysis; Bioinformatics; Biomedical and Life Sciences; Biomedicine; Brain - diagnostic imaging; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Data processing; Efficiency; Humans; Monte Carlo Method; Neuroimaging; Neuroimaging - methods; Neuroimaging - statistics & numerical data; Neurology; Neurosciences; Original Article; Quality control; Leave-one-out (LOO) cross-validation; Linear Mixed-Effects (LME) modeling; Priors; General Linear Model (GLM); Type S and type M errors; Regions of Interest (ROIs); Null Hypothesis Significance Testing (NHST); Stan; False Positive Rate (FPR); Markov Chain Monte Carlo (MCMC); Bayesian Multilevel (BML) modeling
• ISSN: 1539-2791; 1559-0089; 1559-0089
• DOI: 10.1007/s12021-018-9409-6

Here we address the current issues of inefficiency and over-penalization in the massively univariate approach followed by the correction for multiple testing, and propose a more efficient model that pools and shares information among brain regions. Using Bayesian multilevel (BML) modeling, we control two types of error that are more relevant than the conventional false positive rate (FPR): incorrect sign (type S) and incorrect magnitude (type M). BML also aims to achieve two goals: 1) improving modeling efficiency by having one integrative model and thereby dissolving the multiple testing issue, and 2) turning the focus of conventional null hypothesis significant testing (NHST) on FPR into quality control by calibrating type S errors while maintaining a reasonable level of inference efficiency. The performance and validity of this approach are demonstrated through an application at the region of interest (ROI) level, with all the regions on an equal footing: unlike the current approaches under NHST, small regions are not disadvantaged simply because of their physical size. In addition, compared to the massively univariate approach, BML may simultaneously achieve increased spatial specificity and inference efficiency, and promote results reporting in totality and transparency. The benefits of BML are illustrated in performance and quality checking using an experimental dataset. The methodology also avoids the current practice of sharp and arbitrary thresholding in the p -value funnel to which the multidimensional data are reduced. The BML approach with its auxiliary tools is available as part of the AFNI suite for general use.