我們提出嶄新的貝氏階層模型分析具有時間與空間的功能性核磁共振影像資料。在一些研究發現，空間的相依性不只存在於信號變化的大小，同時也發生在時間相關上。然而，在現有大多數研究中為了計算效率而不考慮時間相關上的空間相依性。我們應用空間隨機效果模型(spatial random effect model)同時考慮信號和時間相關的空間相依性。透過模擬，我們發現提出的新方法可以增加識別大腦區域對刺激反應的準確率。最後，我們透過模擬的結果及一個實際的事件相關功能性核磁共振影像資料來探討模型的特性。

We propose a spatial Bayesian hierarchical model to analyze functional magnetic resonance imaging data with complex spatial and temporal structures. Several studies have found that the spatial dependence not only appear in signal changes but also in temporal correlations among voxels. However, currently existing statistical approaches ignore the spatial dependence of temporal correlations for the computational efficiency. We consider the spatial random effect models to simultaneously model spatial dependences in both signal changes and temporal correlations, but keep computationally feasible. Through simulation, the proposed approach improves the accuracy of identifying the activations. We study the properties of the model through its performance on simulations and a real event-related fMRI data set.

Aguirre, G. K., Zarahn, E., and D’Esposito, M. (1997). Empirical analyses of BOLD fMRI statistics. II. Spatially smoothed data collected under null-hypothesis and experimental conditions. NeuroImage, 5:199–212.
Bezener, M., Hughes, J., and Jones, G. L. (2015). Bayesian spatiotemporal modeling using hierarchical spatial priors with applications to functional magnetic resonance imaging.
Bowman, F., Caffo, B., Bassett, S., and Kilts, C. (2008). A bayesian hierarchical frame-work for spatial modeling of fmri data. NeuroImage, 39:146–156.
Caffo, B., Bowman, F., Eberly, L., and Bassett, S. (2011). A markov chain monte carlo based analysis of a multilevel model for functional mri data. In Brooks, S., Gelman,
A., Jones, G., and Meng, X.-L., editors, Handbook of Markov Chain Monte Carlo. CRC Press, Boca Raton, FL.
Detre, J. A. and Floyd, T. (2001). Functional MRI and its applications to the clinical neurosciences. The Neuroscientist, 7:64–79.
Friston, K. J., Ashburner, J. T., Kiebel, S. J., Nichols, T. E., and Penny, W. D. (2007).
Statistical parametric mapping: The analysis of funtional brain images. Elsevier/Aca-demic Press.
Friston, K. J., Fletcher, P., Josephs, O., Holmes, A., Ruggb, M., and Turner, R. (1998).
Event-related fmri: characterizing differential responses. Neuroimage, 7:30–40.
Genovese, C. (2000). A bayesian time-course model for functional magnetic resonance imaging data. Journal of the American Statistical Association, 95:691–703.
George, E. I. and McCulloch, R. E. (1993). Variable selection via gibbs sampling. Journal of the American Statistical Association, 88:881–889.
George, E. I. and McCulloch, R. E. (1997). Approaches for Bayesian variable selection.
Statistica Sinica, 7:339–374.
Glover, G. H. (1999). Decovolution of impulse response in event-related bold. NeuroImage,9:416–429.
Goldsmith, J., Huang, L., and Crainceanu, C. M. (2014). Smooth scalar-on-image regres-sion via spatial bayesian variable selection. Journal of Computational and Graphical Statistics, 23:46–64.
Gössl, C., Fahrmeir, L., and Auer, D. P. (2001). Bayesian spatiotemporal inference in functional magnetic resonance images. Biometric, 57:554–562.
Henson, R., Shallice, T., Gorno-Tempini, M., and Dolan, R. (2002). Face repetition effects in implicit and explicit memory tests as measured by fMRI. Cerebral Cortex,12:178–186.
Hughes, J. and Haran, M. (2013). Dimension reduction and alleviation of confounding for spatial generalized linear mixed models. Journal of the Royal Statistical Society Series B, 75:139–159.
Josephs, O. and Henson, R. (1999). Event-related fmri: modelling, inference and optimi-sation. The Royal Society: Philosopical Transactions B, 354:12151228.
Lee, K., Jones, G. L., Caffo, B., and Bassett, S. (2014). Spatial bayesian variable selection models on functional magnetic resonance imaging time-series data. Bayesian Analysis,9:699–732.
Lindquist, M. A., Atlas, J. M. L. L. Y., and Wager, T. D. (2009). Modeling the hemo-dynamic response function in fmri: Efficiency, bias and mis-modeling. NeuroImage, 45:S187–198.
Lund, T. E., Madsen, K. H., Sidaros, K., Luo, W. L., and Nichols, T. E. (2006). Non-white noise in fmri: Does modelling have an impact? NeuroImage, 29:54–66.
Rajapakse, J. C., Kruggel, F., and Cramon, J. M. M. D. Y. (1998). Modeling hemo-dynamic response for analysis of functional mri time-series. Human Brain Mapping, 6:283–300.
Smith, M. and Fahrmeir, L. (2007). Spatial Bayesian Variable Selection with Application to Functional Magnetic Resonance Imaging. Journal of the American Statistical Asso-ciation, 102:417–431.
Smith, M., Pütz, B., Auer, D., and Fahrmeirc, L. (2003). Assessing brain activity throughspatial Bayesian variable selection. NeuroImage, 20:802–815.
Welvaert, M., Durnez, J., Moerkerke, B., Berdoolaege, G., and Rosseel, Y. (2011). neu-rosim: An r package for generating fmri data. Journal of Statistical Software, 44:1–18.
Woolrich, M., Jenkinson, M., Brady, J., and Smith, S. (2004). Fully Bayesian Spatio-Temporal Modeling for fMRI Data. IEEE Transactions on Medical Imaging, 23:213–231.
Woolrich, M. W., Ripley, B. D., Brady, M., and Smith, S. M. (2001). Temporal autocor-relation in univariate linear modeling of fmri data. NeuroImage, 14:1370–1386.
Xia, J., Liang, F., and Wang, Y. M. (2009). Fmri analysis through Bayesian variable selection with a spatial prior. IEEE Int. Symp. on Biomedical Imaging (ISBI), pages 714–717.
Zhang, L., Guindani, M., and Vannucci, M. (2015). Bayesian models for functional mag-netic resonance imaging data analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 7:21–41.