Time-varying correlation structure estimation and local-feature detection for spatio-temporal data

Spatial–temporal data arise frequently in biomedical, environmental, political and social science studies. Capturing dynamic changes of time-varying correlation structure is scientifically important in spatio-temporal data analysis. We approximate the time-varying empirical estimator of the spatial correlation matrix by groups of selected basis matrices representing substructures of the correlation matrix. After projecting the correlation structure matrix onto a space spanned by basis matrices, we also incorporate varying-coefficient model selection and estimation for signals associated with relevant basis matrices. The unique feature of the proposed method is that signals at local regions corresponding with time can be identified through the proposed penalized objective function. Theoretically, we show model selection consistency and the oracle property in detecting local signals for the varying-coefficient estimators. The proposed method is illustrated through simulation studies and brain fMRI data.

[1]  M. Lindquist.  The Statistical Analysis of fMRI Data. , 2008, 0906.3662.

[2]  Naisyin Wang,et al.  Functional Linear Model with Zero-value Coefficient Function at Sub-regions. , 2013, Statistica Sinica.

[3]  Jianqing Fan,et al.  Sparsistency and Rates of Convergence in Large Covariance Matrix Estimation. , 2007, Annals of statistics.

[4]  Martin A. Lindquist,et al.  Functional Causal Mediation Analysis With an Application to Brain Connectivity , 2012, Journal of the American Statistical Association.

[5]  Correlation structure selection for longitudinal data with diverging cluster size , 2016 .

[6]  Cun-Hui Zhang.  Nearly unbiased variable selection under minimax concave penalty , 2010, 1002.4734.

[7]  Gareth M. James,et al.  Functional linear regression that's interpretable , 2009, 0908.2918.

[8]  Jianqing Fan,et al.  Profile likelihood inferences on semiparametric varying-coefficient partially linear models , 2005 .

[9]  Martin A. Lindquist,et al.  Dynamic connectivity regression: Determining state-related changes in brain connectivity , 2012, NeuroImage.

[10]  Jianhua Z. Huang,et al.  Covariance approximation for large multivariate spatial data sets with an application to multiple climate model errors , 2011, 1203.0133.

[11]  Jianhua Z. Huang,et al.  Varying‐coefficient models and basis function approximations for the analysis of repeated measurements , 2002 .

[12]  R. Tibshirani,et al.  Varying‐Coefficient Models , 1993 .

[13]  Runze Li,et al.  Quadratic Inference Functions for Varying‐Coefficient Models with Longitudinal Data , 2006, Biometrics.

[14]  M. Stein.  Space–Time Covariance Functions , 2005 .

[15]  Yehua Li,et al.  Efficient semiparametric regression for longitudinal data with nonparametric covariance estimation , 2011 .

[16]  Lan Xue,et al.  Variable Selection in High-dimensional Varying-coefficient Models with Global Optimality , 2012, J. Mach. Learn. Res..

[17]  Zhongyi Zhu,et al.  Robust Estimation in Generalized Partial Linear Models for Clustered Data , 2005 .

[18]  Jian Huang,et al.  VARIABLE SELECTION AND ESTIMATION IN HIGH-DIMENSIONAL VARYING-COEFFICIENT MODELS. , 2011, Statistica Sinica.

[19]  Michael Sherman,et al.  A Nonparametric Assessment of Properties of Space–Time Covariance Functions , 2007 .

[20]  Martin A. Lindquist,et al.  Detection of time-varying signals in event-related fMRI designs , 2008, NeuroImage.

[21]  R. Tibshirani,et al.  Sparsity and smoothness via the fused lasso , 2005 .

[22]  Yongtao Guan,et al.  A weighted estimating equation approach for inhomogeneous spatial point processes , 2010 .

[23]  Zhiyi Chi,et al.  Approximating likelihoods for large spatial data sets , 2004 .

[24]  Nicole M. Long,et al.  Journal of the American Statistical Association Spatio-spectral Mixed-effects Model for Functional Magnetic Resonance Imaging Data Spatio-spectral Mixed-effects Model for Functional Magnetic Resonance Imaging Data , 2022 .

[25]  Carl de Boor,et al.  A Practical Guide to Splines , 1978, Applied Mathematical Sciences.

[26]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[27]  Peng Wang,et al.  Estimating and Identifying Unspecified Correlation Structure for Longitudinal Data , 2015, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[28]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[29]  Xiaotong Shen,et al.  Local asymptotics for regression splines and confidence regions , 1998 .

[30]  Mikyoung Jun,et al.  Nonstationary covariance models for global data , 2008, 0901.3980.

[31]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[32]  Yongtao Guan,et al.  Functional Principal Component Analysis of Spatiotemporal Point Processes With Applications in Disease Surveillance , 2014, Journal of the American Statistical Association.

[33]  Bo Li,et al.  An approach to modeling asymmetric multivariate spatial covariance structures , 2011, J. Multivar. Anal..

[34]  B. Lindsay,et al.  Improving generalised estimating equations using quadratic inference functions , 2000 .

[35]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .

[36]  Yongtao Guan.  On Consistent Nonparametric Intensity Estimation for Inhomogeneous Spatial Point Processes , 2008 .

[37]  A. Qu,et al.  Informative Estimation and Selection of Correlation Structure for Longitudinal Data , 2012 .

[38]  R. W. Wedderburn.  Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method , 1974 .