A multivariate spatial mixture model for areal data: examining regional differences in standardized test scores

Researchers in the health and social sciences often wish to examine joint spatial patterns for two or more related outcomes. Examples include infant birth weight and gestational length, psychosocial and behavioral indices, and educational test scores from different cognitive domains. We propose a multivariate spatial mixture model for the joint analysis of continuous individual-level outcomes that are referenced to areal units. The responses are modeled as a finite mixture of multivariate normals, which accommodates a wide range of marginal response distributions and allows investigators to examine covariate effects within subpopulations of interest. The model has a hierarchical structure built at the individual level (i.e., individuals are nested within areal units), and thus incorporates both individual- and areal-level predictors as well as spatial random effects for each mixture component. Conditional autoregressive (CAR) priors on the random effects provide spatial smoothing and allow the shape of the multivariate distribution to vary flexibly across geographic regions. We adopt a Bayesian modeling approach and develop an efficient Markov chain Monte Carlo model fitting algorithm that relies primarily on closed-form full conditionals. We use the model to explore geographic patterns in end-of-grade math and reading test scores among school-age children in North Carolina.

[1]  E. Burmaster.  Department of Public Instruction , 1906 .

[2]  Heikki Haario,et al.  Componentwise adaptation for high dimensional MCMC , 2005, Comput. Stat..

[3]  Vallerie L. Ruiz.  No Child Left Behind Act , 2010 .

[4]  M. Stephens.  Dealing with label switching in mixture models , 2000 .

[5]  Brian J. Reich,et al.  A MULTIVARIATE SEMIPARAMETRIC BAYESIAN SPATIAL MODELING FRAMEWORK FOR HURRICANE SURFACE WIND FIELDS , 2007, 0709.0427.

[6]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[7]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[8]  Majid Jafari Khaledi,et al.  Non-Gaussian modeling of spatial data using scale mixing of a unified skew Gaussian process , 2013, J. Multivar. Anal..

[9]  Jonathan Jacobson,et al.  NATIONAL CENTER FOR EDUCATION STATISTICS , 1998 .

[10]  Bradley P. Carlin,et al.  Bayesian measures of model complexity and fit , 2002 .

[11]  A. Kottas,et al.  Bayesian mixture modeling for spatial Poisson process intensities, with applications to extreme value analysis , 2007 .

[12]  Pulak Ghosh,et al.  Skew-elliptical spatial random effect modeling for areal data with application to mapping health utilization rates. , 2013, Statistics in medicine.

[13]  A. Lawson,et al.  Spatial mixture relative risk models applied to disease mapping , 2002, Statistics in medicine.

[14]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[15]  Devin G. Pope,et al.  Journal of Economic Perspectives—Volume 24, Number 2—Spring 2010—Pages 95–108 Geographic Variation in the Gender Differences in Test Scores , 2022 .

[16]  Bradley P Carlin,et al.  Generalized Hierarchical Multivariate CAR Models for Areal Data , 2005, Biometrics.

[17]  Sw. Banerjee,et al.  Hierarchical Modeling and Analysis for Spatial Data , 2003 .

[18]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[19]  P. Green,et al.  Hidden Markov Models and Disease Mapping , 2002 .

[20]  S. MacEachern,et al.  Bayesian Nonparametric Spatial Modeling With Dirichlet Process Mixing , 2005 .

[21]  Xuan Liu,et al.  Spatial latent class analysis model for spatially distributed multivariate binary data , 2009, Comput. Stat. Data Anal..

[22]  K. Mardia.  Multi-dimensional multivariate Gaussian Markov random fields with application to image processing , 1988 .

[23]  M. Genton,et al.  Probabilistic and Inferential Aspects of Skew-Symmetric Models Special Issue: "IV International Workshop in honour of Adelchi Azzalini's 60th Birthday" Identifiability problems in some non-Gaussian spatial random fields , 2012 .

[24]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[25]  J. Besag,et al.  Bayesian image restoration, with two applications in spatial statistics , 1991 .

[26]  Sudipto Banerjee,et al.  SMOOTHED ANOVA WITH SPATIAL EFFECTS AS A COMPETITOR TO MCAR IN MULTIVARIATE SPATIAL SMOOTHING. , 2010, The annals of applied statistics.

[27]  Aki Vehtari,et al.  Discussion on the paper by Spiegelhalter, Best, Carlin and van der Linde , 2002 .

[28]  Mike West,et al.  Spatial Mixture Modelling for Unobserved Point Processes: Examples in Immunofluorescence Histology. , 2009, Bayesian analysis.

[29]  Ronald F. Ferguson.  Toward Excellence with Equity: An Emerging Vision for Closing the Achievement Gap , 2007 .

[30]  Sylvia Frühwirth-Schnatter,et al.  Finite Mixture and Markov Switching Models , 2006 .

[31]  M. Beg,et al.  A Skew-t space-varying regression model for the spectral analysis of resting state brain activity , 2013, Statistical Methods in Medical Research.

[32]  A. Gelfand,et al.  Proper multivariate conditional autoregressive models for spatial data analysis. , 2003, Biostatistics.

[33]  C. Robert,et al.  Deviance information criteria for missing data models , 2006 .

[34]  Peter Congdon,et al.  Random‐effects models for migration attractivity and retentivity: a Bayesian methodology , 2010 .

[35]  Bradley P. Carlin,et al.  Hierarchical Multivarite CAR Models for Spatio-Temporally Correlated Survival Data , 2002 .

[36]  Jason A. Duan,et al.  Modeling Disease Incidence Data with Spatial and Spatio Temporal Dirichlet Process Mixtures , 2008, Biometrical journal. Biometrische Zeitschrift.